SlideShare a Scribd company logo
Combining Distributional Semantics
and Entity Linking for Context-aware
Content-based Recommendation
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis
(Università degli Studi di Bari ‘Aldo Moro’, Italy - SWAP Research Group)
UMAP 2014
22th Conference on User Modeling,
Adaptation and Personalization
Aalborg (Denmark)
July 8, 2014
Content-based Recommender Systems
Suggest items similar to those the user liked in the past
(I bought Converse should, I’ll continue buying similar sport shoes)
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 2
Content-based Recommender Systems
Xuser profile items
Recommendation are
generated by matching the
features stored in the user
profile with those
describing the items to be
recommended.
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 3
♥
Content-based Recommender Systems
(Some) Limitations
Poor Semantic Representation Poor Contextual Modeling
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 4
?
Lack of Semantics
“I love turkey. It’s my choice for these holidays!
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 5
Lack of Contextual Modeling
Ashtead?
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
in Aalborg:
brewery recommendations
6
Lack of Contextual Modeling
Many content-based recommendation engines
do nothandle contextual information (e.g. user location)
1370km !
far away :-)
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 7
contextual eVSM
a context-aware content-based recommendation
framework based on distributional semantics and
entity linking
Our contribution
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 8
Contextual eVSM
Workflow
Semantic
Content Analyzer
Context-aware
Profiler
Recommender
Items
User
Profiles
User Ratings
Contextual
Data
Item
Description
Context-aware
Recommendations
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 9
Contextual eVSM
3 main components
Semantic !
Content Analyzer!
Context-aware !
Profiler!
Recommender!
Items
User
Profiles
User Ratings
Contextual
Data
Item
Description
Context-aware
Recommendations
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 10
!
• Input: items to be recommended
(along with their textual description)
• Output: semantic representation
• Novelty: we exploited
• Entity Linking algorithms!
• Distributional Semantics Models
Contextual eVSM
Semantic Content Analyzer
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 11
Contextual eVSM
• Entity Linking Algorithms!
• Input: free text.
• items description, in our setting
• Output: identification of the most
relevant entities mentioned in the text.
• We adopted:
• tag.me(1)
,
• DBpedia Spotlight(2)
,
• Wikipedia Miner(3)
Semantic Content Analyzer :: Entity Linking
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
(1) http://tagme.di.unipi.it
(2) http://spotlight.dbpedia.org
(3) http://wikipedia-miner.cms.waikato.ac.nz
12
Contextual eVSM
Semantic Content Analyzer :: Entity Linking::Example
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Textual Description
(e.g. Wikipedia abstract)
Processed Text
13
Contextual eVSM
Semantic Content Analyzer :: Entity Linking::Example
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Very transparent and human readable content representation
Tag.me output
14
Contextual eVSM
Semantic Content Analyzer :: Entity Linking::Example
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Tag.me output
non-trivial NLP tasks (stopwords removal, n-grams identification, named entities
recognition and disambiguation) are automatically performed
15
Very transparent and human readable content representation
Contextual eVSM
Semantic Content Analyzer :: Entity Linking::Example
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Tag.me output
Each entity is a reference to a Wikipedia page
http://en.wikipedia.org/wiki/The_Wachowskis
not a simple textual feature!
16
Contextual eVSM
Semantic Content Analyzer :: Entity Linking::Example
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
We enriched this entity-based representation !
by exploiting the Wikipedia categories’ tree
17
Contextual eVSM
Semantic Content Analyzer :: Entity Linking::Representation
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
The final
representation
of each item is
obtained by
merging the
entities identified
in the text with all
the Wikipedia
categories each
entity is linked to.
+Entities Wikipedia CategoriesFeatures =
18
Contextual eVSM
Semantic Content Analyzer :: Entity Linking::Representation
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
The final
representation
of each item is
obtained by
merging the
entities identified
in the text with all
the Wikipedia
categories each
entity is linked to.
+Entities Wikipedia CategoriesFeatures =
Problem:
Even such a rich, transparent and
human-readable representation
does not handle semantics
19
Contextual eVSM
Semantic Content Analyzer :: Distributional Semantics
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
“meaning
is its use”
L.Wittgenstein
(Austrian philosopher)
20
Contextual eVSM
Semantic Content Analyzer :: Distributional Semantics (*)
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
by analyzing large corpora of
textual data it is possible to
infer information about the
usage (about the meaning) of
the terms
Insight
similar meaning
co-occurrence co-occurrence
co-occurrence co-occurrence
(*) Firth, J.R.A synopsis of linguistic theory
1930-1955. In Studies in Linguistic Analysis, pp.
1-32, 1957.
21
Contextual eVSM
Semantic Content Analyzer :: Distributional Semantics::WordSpace
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
beer
wine
mojito
dog
22
Vector-space
representation is based on
term co-occurences
Contextual eVSM
Semantic Content Analyzer :: Distributional Semantics
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
e1 e2 e3 e4 e5 e6 e7 e8 e9
Keanu Reeves ✔ ✔ ✔ ✔ ✔
Al Pacino ✔ ✔
American Writers ✔ ✔ ✔ ✔
Laurence Fishburne ✔ ✔ ✔ ✔
Our Semantic Content Analyzer learns a vector-space item
representation based on distributional semantics models
23
Contextual eVSM
Semantic Content Analyzer :: Distributional Semantics
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
e1 e2 e3 e4 e5 e6 e7 e8 e9
Keanu Reeves ✔ ✔ ✔ ✔ ✔
Al Pacino ✔ ✔
American Writers ✔ ✔ ✔ ✔
Laurence Fishburne ✔ ✔ ✔ ✔
Vector-space Semantic Representation is learnt according to
entities co-occurrences in textual descriptions
24
Contextual eVSM
Semantic Content Analyzer :: Distributional Semantics
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Unexpected connections between
entities can be learnt in a total
unsupervised way thanks to
Distributional Semantics
25
Contextual eVSM
Semantic Content Analyzer :: Distributional Semantics
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
e1 e2 e3 e4 e5 e6 e7 e8 e9
Keanu Reeves ✔ ✔ ✔ ✔ ✔
Al Pacino ✔ ✔
American Writers ✔ ✔ ✔ ✔
Laurence Fishburne ✔ ✔ ✔ ✔
e.g. Keanu Reeves and Al
Pacino both starred in
Drama movies
26
Contextual eVSM
Semantic Content Analyzer :: Distributional Semantics
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
How to exploit
Distributional Semantics !
to represent items
to be recommended?
Question
27
Contextual eVSM
Semantic Content Analyzer :: Distributional Semantics
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
e1 e2 e3 e4 e5 e6 e7 e8 e9
Keanu Reeves ✔ ✔ ✔ ✔ ✔
Drama ✔ ✔
American Writers ✔ ✔ ✔ ✔
Laurence Fishburne ✔ ✔ ✔ ✔
semantic representation of the items is obtained by combining
the vector-space representation of the features which
describe them.
28
Contextual eVSM
Semantic Content Analyzer :: Distributional Semantics
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
e1 e2 e3 e4 e5 e6 e7 e8 e9
Keanu Reeves ✔ ✔ ✔ ✔ ✔
Al Pacino ✔ ✔
American Writers ✔ ✔ ✔ ✔
Laurence Fishburne ✔ ✔ ✔ ✔
Matrix ✔ ✔ ✔ ✔ ✔ ✔ ✔ ✔
29
Contextual eVSM
Semantic Content Analyzer :: Distributional Semantics
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Matrix
Matrix Revolutions
Donnie Darko
Up!
It is possible to
perform similarity
calculations
between items
according to their
semantic
representation
30
!
• Input:
• user preferences (ratings)
• contextual information
• Fixed set of contextual dimensions
(company, mood, task, etc.)
• Fixed set of values (e.g. company=alone,
friends, girlfriend, etc.)
• Output: contextual user profiles
• Novelty: we introduced a Context-aware
Profiling Strategy based on Distributional
Models
Contextual eVSM
Context-aware Profiler
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 31
C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj)
Contextual eVSM
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Context-aware User Profiler :: Strategy
Let’s go straight to the formula
32
Contextual eVSM
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Context-aware User Profiler :: Strategy
Let u be the target user
Let ck be a contextual variable (e.g. task, mood, etc.)
Let vj be its value (e.g. task=running, mood=sad, etc.)
33
C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj)
Contextual eVSM
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Context-aware User Profiler :: Strategy
C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj)
A context-aware profile can be learnt by combining
two components in a linear fashion
34
Contextual eVSM
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Context-aware User Profiler :: Strategy
C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj)
a non-contextual representation
of user preferences
a vector space representation of
the context itself
35
A context-aware profile can be learnt by combining
two components in a linear fashion
Contextual eVSM
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Context-aware User Profiler :: Strategy :: WRI(u)
C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj)
WRI(u) = ∑ di*
r(u,i)
MAXi=1
|L|
NON-CONTEXTUAL USER
PREFERENCES
36
Contextual eVSM
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Context-aware User Profiler :: Strategy :: WRI(u)
C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj)
WRI(u) = ∑ di*
r(u,i)
MAXi=1
|L|
items the user liked
37
Contextual eVSM
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Context-aware User Profiler :: Strategy :: WRI(u)
C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj)
WRI(u) = ∑ di*
r(u,i)
MAXi=1
|L| vector-space representation of the
item built by Semantic Content
Analyzer
38
Contextual eVSM
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Context-aware User Profiler :: Strategy :: WRI(u)
C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj)
WRI(u) = ∑ di*
r(u,i)
MAXi=1
|L|
normalized rating
39
Contextual eVSM
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Context-aware User Profiler :: Strategy :: context(u,ck,vj)
C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj)
context(u,ck,vj) = ∑ di*
r(u,i,ck,vj)
MAXi=1
|L(ck,vj)| Vector-space
representation of
the context
40
Contextual eVSM
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj)
context(u,ck,vj) = ∑ di*
r(u,i,ck,vj)
MAXi=1
|L(ck,vj)|
items the user liked
in that specific context
Context-aware User Profiler :: Strategy :: context(u,ck,vj)
41
r(u,i,ck,vj)
Contextual eVSM
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj)
context(u,ck,vj) = ∑ di*
MAXi=1
|L(ck,vj)| vector space
representation
of the item
Context-aware User Profiler :: Strategy :: context(u,ck,vj)
42
Contextual eVSM
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj)
context(u,ck,vj) = ∑ di*
r(u,i,ck,vj)
MAXi=1
|L(ck,vj)|
normalized rating
in that specific context
Context-aware User Profiler :: Strategy :: context(u,ck,vj)
43
Contextual eVSM
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Context-aware User Profiler :: Strategy
C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj)
Ratio: context is just a factor which can influence
user’s perception of an item
44
Contextual eVSM
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Context-aware User Profiler :: Strategy
if the user did not express any preference in that
specific contextual setting, context(u,ck,vj) = 0 !
—> non contextual recommendation
C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj)
Ratio: context is just a factor which can influence
user’s perception of an item
45
X
Contextual eVSM
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Context-aware User Profiler :: Strategy
Otherwise parameter α is exploited to tune a
specific component of the formula
Ratio: context is just a factor which can influence
user’s perception of an item
46
C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj)
Contextual eVSM
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Context-aware User Profiler :: How do we come to this formula?
C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj)
47
C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj)
Contextual eVSM
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Context-aware User Profiler :: How do we come to this formula?
Insight: it exists a set of terms that is more descriptive of
items relevant in that specific context
for a romantic dinner, e.g. candlelight, seaview, violin
48
e.g. task = dinner, company=girlfriend
Context is represented on the
ground of the items the user
liked in that specific contextual setting
Contextual eVSM
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Context-aware User Profiler :: Our formula inherits this insight
49
r(u,i,ck,vj)
MAXi=1
|L(ck,vj)|
context(u,ck,vj) = ∑ di*
Context is represented on the
ground of the items the user
liked in that specific contextual setting
Contextual eVSM
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 50
r(u,i,ck,vj)
MAX
Items are represented on the ground of
the co-occurrences between entities
i=1
|L(ck,vj)|
context(u,ck,vj) = ∑ di*
Context-aware User Profiler :: Our formula inherits this insight
Context is represented on the
ground of the items the user
liked in that specific contextual setting
Contextual eVSM
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 51
r(u,i,ck,vj)
MAX
Items are represented on the ground of
the co-occurrences between entities
i=1
|L(ck,vj)|
context(u,ck,vj) = ∑ di*
the resulting representation of
the context is such that a
bigger weight is given to the
entities which typically
occur in the description of
the items relevant in that
specific context
Context-aware User Profiler :: Our formula inherits this insight
context(u,ck,vj) = ∑ di*
Contextual eVSM
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 52
r(u,i,ck,vj)
MAX
Thanks to Distributional Semantics Models it is possible
to build a vector-space representation of the context
which emphasize the importance of those terms,
since they are more used (—> more important) in that
specific contextual setting.
i=1
|L(ck,vj)|
Context-aware User Profiler :: Our formula inherits this insight
Contextual eVSM
Recommendation step
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Skyfall
WRI(u)
Austin Powers
Up!
The goal of our
context-aware
profiling strategy is to
perturb the
representation of user
preferences and to
provide him with
context-aware
recommendations
53
non-contextual preferences
Contextual eVSM
Recommendation step
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Skyfall
C-WRI(u)
Austin Powers
Up!
The goal of our
context-aware
profiling strategy is to
perturb the
representation of user
preferences and to
provide him with
context-aware
recommendations
54
contextual preferences
(e.g. company = friends)
Experimental Evaluation
Research Hypothesis
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 55
1. Does C-eVSM outperform its
non-contextual counterpart?
2. Does the novel representation
based on entity linking and
distributional semantics
outperform a simple keyword-
based one?
3. How does our model perform with
respect to the current literature?
Experimental Evaluation
Description of the dataset
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 56
• Movie recommendation!
• Subset of IMDB data
• 202 movies (textual features crawled
from Wikipedia)
• 62 users and 1457 ratings!
• 4 contextual dimensions!
• TIME (weekend, weekday)
• PLACE (theather, home)
• COMPANION (alone, friends, boyfriend,
family)
• MOVIE-RELATED (release week or not)
Experimental Evaluation
Design of the Experiment
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 57
• Dataset and experimental settings
replicate Adomavicius’ experiment (*)!
• Evaluation over 9 different contextual
settings!
• Home, Friends, Non-release, Weekend,
Weekday, GBFriends, TheatherWeekend
and TheatherFriends
• Metric: F1-Measure
• Experimental protocol: bootstrapping!
• 29/30th of the data as training
• 1/30th as test
• Randomly generated, 500 runs
(*) G.Adomavicius et al. , Incorporating contextual information
in recommender systems using a multi-dimensional
approach.ACM Trans. Inf. Systems, 2005
Experimental Evaluation
eVSM configurations
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 58
• Non-contextual baseline: eVSM!
• WRI profiling strategy
• WQN profiling strategy
• Context-aware framework: C-
eVSM!
• C-WRI profiling strategy
• C-WQN profiling strategy
• Three values for parameter α!
• 0.2 , 0.5, 0.8
8 configurations
for each run
Experimental Evaluation
eVSM configurations
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 59
• Non-contextual baseline: eVSM!
• WRI profiling strategy
• WQN profiling strategy
• Context-aware framework: C-
eVSM!
• C-WRI profiling strategy
• C-WQN profiling strategy
• Three values for parameter α!
• 0.2 , 0.5, 0.8
• WQN!
• Alternative profiling strategy (*)
• Models negative user
feedbacks as well
• Combines positive and
negative preferences by
means of a Quantum
Negation (**) Operator
(*) C. Musto, G. Semeraro, P. Lops, and M. de Gemmis. Random indexing and 

negative user preferences for enhancing content-based recommender
systems. In EC-Web 2011, volume 85 of LNBIP, pages 270–281. 2011.
(**) D. Widdows. Orthogonal negation in vector spaces for modelling word-
meanings and document retrieval. In ACL, pages 136–143, 2003.
Experiment 1
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 60
Comparison of C-eVSM vs eVSM (keyword-based)
Experiment 1
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 61
Selection of Results :: HOME segment
WRI
C-WRI-0.2
C-WRI-0.5
C-WRI-0.8
WQN
C-WQN-0.2
C-WQN-0.5
C-WQN-0.8
45 48,75 52,5 56,25 60
58,8
57,82
54,81
53,62
50,6
48,23
46,62
47,62
contextual eVSM improves the F1 measure
Experiment 1
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 62
Selection of Results :: HOME segment
WRI
C-WRI-0.2
C-WRI-0.5
C-WRI-0.8
WQN
C-WQN-0.2
C-WQN-0.5
C-WQN-0.8
45 48,75 52,5 56,25 60
58,8
57,82
54,81
53,62
50,6
48,23
46,62
47,62
contextual eVSM improves the F1 measure
paired t-test (p<0.05)
baseline
baseline
Experiment 1
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 63
Selection of Results :: HOME segment
WRI
C-WRI-0.2
C-WRI-0.5
C-WRI-0.8
WQN
C-WQN-0.2
C-WQN-0.5
C-WQN-0.8
45 48,75 52,5 56,25 60
58,8
57,82
54,81
53,62
50,6
48,23
46,62
47,62
α=0.8 is better than α=0.5
WRI
C-WRI-0.2
C-WRI-0.5
C-WRI-0.8
WQN
C-WQN-0.2
C-WQN-0.5
C-WQN-0.8
42,0 45,3 48,5 51,8 55,0
54,39
50,04
45,93
53,18
50,11
50,54
44,91
49,43
Experiment 1
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 64
Selection of Results :: FRIENDS segment
Similar outcomes: C-eVSM outperforms eVSM
paired t-test (p<0.05)
WRI
C-WRI-0.2
C-WRI-0.5
C-WRI-0.8
WQN
C-WQN-0.2
C-WQN-0.5
C-WQN-0.8
42,0 45,3 48,5 51,8 55,0
54,39
50,04
45,93
53,18
50,11
50,54
44,91
49,43
Experiment 1
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 65
Selection of Results :: FRIENDS segment
α=0.2 does not improve F1-measure
WRI
C-WRI-0.2
C-WRI-0.5
C-WRI-0.8
WQN
C-WQN-0.2
C-WQN-0.5
C-WQN-0.8
42,0 45,8 49,5 53,3 57,0
56,78
52,55
48,67
55,94
52,18
49,05
48,24
48,95
Experiment 1
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 66
Selection of Results :: NON-RELEASE segment
C-WQN with α=0.8 is typically the best-performing configuration
paired t-test (p<0.05)
WRI
C-WRI-0.2
C-WRI-0.5
C-WRI-0.8
WQN
C-WQN-0.2
C-WQN-0.5
C-WQN-0.8
42,0 45,8 49,5 53,3 57,0
56,78
52,55
48,67
55,94
52,18
49,05
48,24
48,95
Experiment 1
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 67
Selection of Results :: NON-RELEASE segment
Outcome: context has just to slightly influence user preferences
Experiment 1
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 68
Outcomes
• Contextual eVSM outperforms eVSM
• 8 segments out of 9
• Little statistical significance
• Negation is useful when dataset is well-balanced
• Higher α values lead to a better F1
• Best-performing configurations are C-WQN-0.8 (4
times), C-WRI-0.8 (1 times), C-WRI-0.5 (3 times)
Experiment 2
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 69
Comparison of entity-based vs keyword-based
content representation
Experiment 2
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 70
WRI
C-WRI-0.2
C-WRI-0.5
C-WRI-0.8
WQN
C-WQN-0.2
C-WQN-0.5
C-WQN-0.8
40,0 47,5 55,0 62,5 70,0
61,30
61,96
54,81
57,53
56,75
56,38
46,62
56,13
58,80
57,82
53,37
53,62
50,60
48,23
44,56
47,62 Keywords
Entities
Selection of Results :: HOME segment
Semantic representation improves F1 in all the configurations
Experiment 2
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 71
Selection of Results :: HOME segment
Gaps are significant in 5 out of 8 configurations
WRI
C-WRI-0.2
C-WRI-0.5
C-WRI-0.8
WQN
C-WQN-0.2
C-WQN-0.5
C-WQN-0.8
40,0 47,5 55,0 62,5 70,0
61,3
61,96
54,81
57,53
56,75
56,38
46,62
56,13
58,80
57,82
53,37
53,62
50,60
48,23
44,56
47,62 Keywords
Entities
WRI
C-WRI-0.2
C-WRI-0.5
C-WRI-0.8
WQN
C-WQN-0.2
C-WQN-0.5
C-WQN-0.8
40,0 47,5 55,0 62,5 70,0
61,3
61,96
54,81
57,53
56,75
56,38
46,62
56,13
58,80
57,82
53,37
53,62
50,60
48,23
44,56
47,62 Keywords
Entities
Experiment 2
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 72
Selection of Results :: HOME segment
Again, higher α values lead to the best F1-measure scores
WRI
C-WRI-0.2
C-WRI-0.5
C-WRI-0.8
WQN
C-WQN-0.2
C-WQN-0.5
C-WQN-0.8
43,0 48,5 54,0 59,5 65,0
58,37
57,2
52,82
58,25
55,68
56,24
49,19
56,17
54,39
50,04
45,93
53,18
50,11
50,54
44,91
49,43 Keywords
Entities
Experiment 2
73
Selection of Results :: FRIEND segment
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
+6,42%improvement, gap always significant
WRI
C-WRI-0.2
C-WRI-0.5
C-WRI-0.8
WQN
C-WQN-0.2
C-WQN-0.5
C-WQN-0.8
43,0 48,5 54,0 59,5 65,0
58,37
57,2
52,82
58,25
55,68
56,24
49,19
56,17
54,39
50,04
45,93
53,18
50,11
50,54
44,91
49,43 Keywords
Entities
Experiment 2
74
Selection of Results :: FRIEND segment
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Negation+ α Higher values ➝ best configuration
WRI
C-WRI-0.2
C-WRI-0.5
C-WRI-0.8
WQN
C-WQN-0.2
C-WQN-0.5
C-WQN-0.8
43,0 48,5 54,0 59,5 65,0
62,16
57,81
54,72
56,45
58,11
57,21
55,82
56,34
52,64
51,40
46,65
50,71
52,87
53,95
52,79
50,91 Keywords
Entities
Experiment 2
75
Selection of Results :: THEATER segment
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Best perfoming segment: +6,49% improvement over keywords
WRI
C-WRI-0.2
C-WRI-0.5
C-WRI-0.8
WQN
C-WQN-0.2
C-WQN-0.5
C-WQN-0.8
43,0 48,5 54,0 59,5 65,0
62,16
57,81
54,72
56,45
58,11
57,21
55,82
56,34
52,64
51,40
46,65
50,71
52,87
53,95
52,79
50,91 Keywords
Entities
Experiment 2
76
Selection of Results :: THEATER segment
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
C-WQN is the best perfoming configuration: +9,52%
Experiment 2
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 77
Outcomes
• Novel semantic representation outperforms the keyword-based one
• 7 segments out of 9
• +4% on average, eanging from +1,34% to +6,49%
• Important gaps in terms of F1-measure
• Entity-based outperforms keywords in 65 segments out of 90 (72%)
• Statistically significant gap in 52 out of 90 of the comparisons (58%)
• Negation and higher α values lead to a better F1
• Best-performing configurations are C-WQN-0.8 (3 times), C-WQN-0.5 (2
times), C-WRI-0.5 (2 times)
Experiment 3
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 78
Comparison to context-aware CF algorithm(*)
(*) G.Adomavicius et al. , Incorporating contextual
information in recommender systems using a multi-
dimensional approach.ACM Trans. Inf. Systems, 2005
Home
Friends
Weekend
Theater
Nonrelease
Weekday
GBFriends
Theater-Weekend
Theater-Friends
35,0 43,8 52,5 61,3 70,0
60,7
64,1
48
37,9
43,2
60,8
54,2
48,2
39,19
55,96
54,95
50,72
48,02
57,01
61,16
60,39
58,37
61,96
c-eVSM
CACF
Experiment 3
79Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Comparison to context-aware CF algorithm
Contextual eVSM overcomes CACF in 7 segments out of 9
✔
Home
Friends
Weekend
Theater
Nonrelease
Weekday
GBFriends
Theater-Weekend
Theater-Friends
35,0 43,8 52,5 61,3 70,0
60,7
64,1
48
37,9
43,2
60,8
54,2
48,2
39,19
55,96
54,95
50,72
48,02
57,01
61,16
60,39
58,37
61,96
c-eVSM
CACF
Experiment 3
80Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Comparison to context-aware CF algorithm
Gap is statistically significant in 5 segments out of 7
Recap
81Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Recap
82Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Contextual eVSM: context-aware recommendation framework
Content Representation based on Distributional Semantics and Entity Linking
Profile Learning based on a perturbation of non-contextual preferences with a
semantic representation of the context!
Experimental session confirmed the effectiveness of the framework as well as of
the novel semantic representation!
Framework overcomes a context-aware collaborative filtering baseline
Future Research
83Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Future Research
84Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and
Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
Evaluation against different
datasets and stronger baselines;
Exploitation of Linked Data and
Open Knowledge Sources for
content representation;
Evaluation of Novelty, Diversity and
Serendipity of the Recommendations;
questions?
Cataldo Musto, Ph.D
cataldo.musto@uniba.it

More Related Content

Viewers also liked

Entity linking meets Word Sense Disambiguation: a unified approach(TACL 2014)の紹介
Entity linking meets Word Sense Disambiguation: a unified approach(TACL 2014)の紹介Entity linking meets Word Sense Disambiguation: a unified approach(TACL 2014)の紹介
Entity linking meets Word Sense Disambiguation: a unified approach(TACL 2014)の紹介
Koji Matsuda
 
OUTDATED Text Mining 5/5: Information Extraction
OUTDATED Text Mining 5/5: Information ExtractionOUTDATED Text Mining 5/5: Information Extraction
OUTDATED Text Mining 5/5: Information Extraction
Florian Leitner
 
Textmining Information Extraction
Textmining Information ExtractionTextmining Information Extraction
Textmining Information Extraction
guest0edcaf
 
Information Extraction with UIMA - Usecases
Information Extraction with UIMA - UsecasesInformation Extraction with UIMA - Usecases
Information Extraction with UIMA - Usecases
Tommaso Teofili
 
Data and Information Extraction on the Web
Data and Information Extraction on the WebData and Information Extraction on the Web
Data and Information Extraction on the Web
Tommaso Teofili
 
Martin Voigt | Streaming-based Text Mining using Deep Learning and Semantics
Martin Voigt | Streaming-based Text Mining using Deep Learning and SemanticsMartin Voigt | Streaming-based Text Mining using Deep Learning and Semantics
Martin Voigt | Streaming-based Text Mining using Deep Learning and Semantics
semanticsconference
 

Viewers also liked (6)

Entity linking meets Word Sense Disambiguation: a unified approach(TACL 2014)の紹介
Entity linking meets Word Sense Disambiguation: a unified approach(TACL 2014)の紹介Entity linking meets Word Sense Disambiguation: a unified approach(TACL 2014)の紹介
Entity linking meets Word Sense Disambiguation: a unified approach(TACL 2014)の紹介
 
OUTDATED Text Mining 5/5: Information Extraction
OUTDATED Text Mining 5/5: Information ExtractionOUTDATED Text Mining 5/5: Information Extraction
OUTDATED Text Mining 5/5: Information Extraction
 
Textmining Information Extraction
Textmining Information ExtractionTextmining Information Extraction
Textmining Information Extraction
 
Information Extraction with UIMA - Usecases
Information Extraction with UIMA - UsecasesInformation Extraction with UIMA - Usecases
Information Extraction with UIMA - Usecases
 
Data and Information Extraction on the Web
Data and Information Extraction on the WebData and Information Extraction on the Web
Data and Information Extraction on the Web
 
Martin Voigt | Streaming-based Text Mining using Deep Learning and Semantics
Martin Voigt | Streaming-based Text Mining using Deep Learning and SemanticsMartin Voigt | Streaming-based Text Mining using Deep Learning and Semantics
Martin Voigt | Streaming-based Text Mining using Deep Learning and Semantics
 

Similar to Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendation

Tuning Personalized PageRank for Semantics-aware Recommendations based on Lin...
Tuning Personalized PageRank for Semantics-aware Recommendations based on Lin...Tuning Personalized PageRank for Semantics-aware Recommendations based on Lin...
Tuning Personalized PageRank for Semantics-aware Recommendations based on Lin...
Cataldo Musto
 
AMBIGUITY-AWARE DOCUMENT SIMILARITY
AMBIGUITY-AWARE DOCUMENT SIMILARITYAMBIGUITY-AWARE DOCUMENT SIMILARITY
AMBIGUITY-AWARE DOCUMENT SIMILARITY
ijnlc
 
IJNLC 2013 - Ambiguity-Aware Document Similarity
IJNLC  2013 - Ambiguity-Aware Document SimilarityIJNLC  2013 - Ambiguity-Aware Document Similarity
IJNLC 2013 - Ambiguity-Aware Document Similarity
kevig
 
Detection of Verbal Multi-Word Expressions via Conditional Random Fields with...
Detection of Verbal Multi-Word Expressions via Conditional Random Fields with...Detection of Verbal Multi-Word Expressions via Conditional Random Fields with...
Detection of Verbal Multi-Word Expressions via Conditional Random Fields with...
Lifeng (Aaron) Han
 
Continuous bag of words cbow word2vec word embedding work .pdf
Continuous bag of words cbow word2vec word embedding work .pdfContinuous bag of words cbow word2vec word embedding work .pdf
Continuous bag of words cbow word2vec word embedding work .pdf
devangmittal4
 
SPIMBENCH: A Scalable, Schema-Aware Instance Matching Benchmark for the Seman...
SPIMBENCH: A Scalable, Schema-Aware Instance Matching Benchmark for the Seman...SPIMBENCH: A Scalable, Schema-Aware Instance Matching Benchmark for the Seman...
SPIMBENCH: A Scalable, Schema-Aware Instance Matching Benchmark for the Seman...
Graph-TA
 
SPIMBENCH: A scalable, Schema-Aware Instance Matching Benchmark for the Seman...
SPIMBENCH: A scalable, Schema-Aware Instance Matching Benchmark for the Seman...SPIMBENCH: A scalable, Schema-Aware Instance Matching Benchmark for the Seman...
SPIMBENCH: A scalable, Schema-Aware Instance Matching Benchmark for the Seman...
Ioan Toma
 
SPIMBENCH: A scalable, Schema-Aware Instance Matching Benchmark for the Seman...
SPIMBENCH: A scalable, Schema-Aware Instance Matching Benchmark for the Seman...SPIMBENCH: A scalable, Schema-Aware Instance Matching Benchmark for the Seman...
SPIMBENCH: A scalable, Schema-Aware Instance Matching Benchmark for the Seman...
LDBC council
 
Semantics-aware Graph-based Recommender Systems exploiting Linked Open Data
Semantics-aware Graph-based Recommender Systems exploiting Linked Open DataSemantics-aware Graph-based Recommender Systems exploiting Linked Open Data
Semantics-aware Graph-based Recommender Systems exploiting Linked Open Data
Cataldo Musto
 
VIDEO OBJECTS DESCRIPTION IN HINDI TEXT LANGUAGE
VIDEO OBJECTS DESCRIPTION IN HINDI TEXT LANGUAGE VIDEO OBJECTS DESCRIPTION IN HINDI TEXT LANGUAGE
VIDEO OBJECTS DESCRIPTION IN HINDI TEXT LANGUAGE
ijmpict
 
G04124041046
G04124041046G04124041046
G04124041046
IOSR-JEN
 
Exploiting Distributional Semantics Models for Natural Language Context-aware...
Exploiting Distributional Semantics Models for Natural Language Context-aware...Exploiting Distributional Semantics Models for Natural Language Context-aware...
Exploiting Distributional Semantics Models for Natural Language Context-aware...
Cataldo Musto
 
COMMENT POLARITY MOVIE RATING SYSTEM-1.pptx
COMMENT POLARITY MOVIE RATING SYSTEM-1.pptxCOMMENT POLARITY MOVIE RATING SYSTEM-1.pptx
COMMENT POLARITY MOVIE RATING SYSTEM-1.pptx
5088manoj
 
Supporting User's Exploration of Digital Libraries, Suedl 2012 workshop proce...
Supporting User's Exploration of Digital Libraries, Suedl 2012 workshop proce...Supporting User's Exploration of Digital Libraries, Suedl 2012 workshop proce...
Supporting User's Exploration of Digital Libraries, Suedl 2012 workshop proce...
pathsproject
 
Semantic Similarity Assessment to Browse Resources exposed as Linked Data: an...
Semantic Similarity Assessment to Browse Resources exposed as Linked Data: an...Semantic Similarity Assessment to Browse Resources exposed as Linked Data: an...
Semantic Similarity Assessment to Browse Resources exposed as Linked Data: an...
Riccardo Albertoni
 
Towards a Distributional Semantic Web Stack
Towards a Distributional Semantic Web StackTowards a Distributional Semantic Web Stack
Towards a Distributional Semantic Web Stack
Andre Freitas
 
Improving Text Categorization with Semantic Knowledge in Wikipedia
Improving Text Categorization with Semantic Knowledge in WikipediaImproving Text Categorization with Semantic Knowledge in Wikipedia
Improving Text Categorization with Semantic Knowledge in Wikipedia
chjshan
 
THE ABILITY OF WORD EMBEDDINGS TO CAPTURE WORD SIMILARITIES
THE ABILITY OF WORD EMBEDDINGS TO CAPTURE WORD SIMILARITIESTHE ABILITY OF WORD EMBEDDINGS TO CAPTURE WORD SIMILARITIES
THE ABILITY OF WORD EMBEDDINGS TO CAPTURE WORD SIMILARITIES
kevig
 
THE ABILITY OF WORD EMBEDDINGS TO CAPTURE WORD SIMILARITIES
THE ABILITY OF WORD EMBEDDINGS TO CAPTURE WORD SIMILARITIESTHE ABILITY OF WORD EMBEDDINGS TO CAPTURE WORD SIMILARITIES
THE ABILITY OF WORD EMBEDDINGS TO CAPTURE WORD SIMILARITIES
kevig
 
Semantic annotation of biomedical data
Semantic annotation of biomedical dataSemantic annotation of biomedical data
Semantic annotation of biomedical data
INRAE (MISTEA) and University of Montpellier (LIRMM)
 

Similar to Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendation (20)

Tuning Personalized PageRank for Semantics-aware Recommendations based on Lin...
Tuning Personalized PageRank for Semantics-aware Recommendations based on Lin...Tuning Personalized PageRank for Semantics-aware Recommendations based on Lin...
Tuning Personalized PageRank for Semantics-aware Recommendations based on Lin...
 
AMBIGUITY-AWARE DOCUMENT SIMILARITY
AMBIGUITY-AWARE DOCUMENT SIMILARITYAMBIGUITY-AWARE DOCUMENT SIMILARITY
AMBIGUITY-AWARE DOCUMENT SIMILARITY
 
IJNLC 2013 - Ambiguity-Aware Document Similarity
IJNLC  2013 - Ambiguity-Aware Document SimilarityIJNLC  2013 - Ambiguity-Aware Document Similarity
IJNLC 2013 - Ambiguity-Aware Document Similarity
 
Detection of Verbal Multi-Word Expressions via Conditional Random Fields with...
Detection of Verbal Multi-Word Expressions via Conditional Random Fields with...Detection of Verbal Multi-Word Expressions via Conditional Random Fields with...
Detection of Verbal Multi-Word Expressions via Conditional Random Fields with...
 
Continuous bag of words cbow word2vec word embedding work .pdf
Continuous bag of words cbow word2vec word embedding work .pdfContinuous bag of words cbow word2vec word embedding work .pdf
Continuous bag of words cbow word2vec word embedding work .pdf
 
SPIMBENCH: A Scalable, Schema-Aware Instance Matching Benchmark for the Seman...
SPIMBENCH: A Scalable, Schema-Aware Instance Matching Benchmark for the Seman...SPIMBENCH: A Scalable, Schema-Aware Instance Matching Benchmark for the Seman...
SPIMBENCH: A Scalable, Schema-Aware Instance Matching Benchmark for the Seman...
 
SPIMBENCH: A scalable, Schema-Aware Instance Matching Benchmark for the Seman...
SPIMBENCH: A scalable, Schema-Aware Instance Matching Benchmark for the Seman...SPIMBENCH: A scalable, Schema-Aware Instance Matching Benchmark for the Seman...
SPIMBENCH: A scalable, Schema-Aware Instance Matching Benchmark for the Seman...
 
SPIMBENCH: A scalable, Schema-Aware Instance Matching Benchmark for the Seman...
SPIMBENCH: A scalable, Schema-Aware Instance Matching Benchmark for the Seman...SPIMBENCH: A scalable, Schema-Aware Instance Matching Benchmark for the Seman...
SPIMBENCH: A scalable, Schema-Aware Instance Matching Benchmark for the Seman...
 
Semantics-aware Graph-based Recommender Systems exploiting Linked Open Data
Semantics-aware Graph-based Recommender Systems exploiting Linked Open DataSemantics-aware Graph-based Recommender Systems exploiting Linked Open Data
Semantics-aware Graph-based Recommender Systems exploiting Linked Open Data
 
VIDEO OBJECTS DESCRIPTION IN HINDI TEXT LANGUAGE
VIDEO OBJECTS DESCRIPTION IN HINDI TEXT LANGUAGE VIDEO OBJECTS DESCRIPTION IN HINDI TEXT LANGUAGE
VIDEO OBJECTS DESCRIPTION IN HINDI TEXT LANGUAGE
 
G04124041046
G04124041046G04124041046
G04124041046
 
Exploiting Distributional Semantics Models for Natural Language Context-aware...
Exploiting Distributional Semantics Models for Natural Language Context-aware...Exploiting Distributional Semantics Models for Natural Language Context-aware...
Exploiting Distributional Semantics Models for Natural Language Context-aware...
 
COMMENT POLARITY MOVIE RATING SYSTEM-1.pptx
COMMENT POLARITY MOVIE RATING SYSTEM-1.pptxCOMMENT POLARITY MOVIE RATING SYSTEM-1.pptx
COMMENT POLARITY MOVIE RATING SYSTEM-1.pptx
 
Supporting User's Exploration of Digital Libraries, Suedl 2012 workshop proce...
Supporting User's Exploration of Digital Libraries, Suedl 2012 workshop proce...Supporting User's Exploration of Digital Libraries, Suedl 2012 workshop proce...
Supporting User's Exploration of Digital Libraries, Suedl 2012 workshop proce...
 
Semantic Similarity Assessment to Browse Resources exposed as Linked Data: an...
Semantic Similarity Assessment to Browse Resources exposed as Linked Data: an...Semantic Similarity Assessment to Browse Resources exposed as Linked Data: an...
Semantic Similarity Assessment to Browse Resources exposed as Linked Data: an...
 
Towards a Distributional Semantic Web Stack
Towards a Distributional Semantic Web StackTowards a Distributional Semantic Web Stack
Towards a Distributional Semantic Web Stack
 
Improving Text Categorization with Semantic Knowledge in Wikipedia
Improving Text Categorization with Semantic Knowledge in WikipediaImproving Text Categorization with Semantic Knowledge in Wikipedia
Improving Text Categorization with Semantic Knowledge in Wikipedia
 
THE ABILITY OF WORD EMBEDDINGS TO CAPTURE WORD SIMILARITIES
THE ABILITY OF WORD EMBEDDINGS TO CAPTURE WORD SIMILARITIESTHE ABILITY OF WORD EMBEDDINGS TO CAPTURE WORD SIMILARITIES
THE ABILITY OF WORD EMBEDDINGS TO CAPTURE WORD SIMILARITIES
 
THE ABILITY OF WORD EMBEDDINGS TO CAPTURE WORD SIMILARITIES
THE ABILITY OF WORD EMBEDDINGS TO CAPTURE WORD SIMILARITIESTHE ABILITY OF WORD EMBEDDINGS TO CAPTURE WORD SIMILARITIES
THE ABILITY OF WORD EMBEDDINGS TO CAPTURE WORD SIMILARITIES
 
Semantic annotation of biomedical data
Semantic annotation of biomedical dataSemantic annotation of biomedical data
Semantic annotation of biomedical data
 

More from Cataldo Musto

MyrrorBot: a Digital Assistant Based on Holistic User Models for Personalize...
MyrrorBot: a Digital Assistant Based on Holistic User Models forPersonalize...MyrrorBot: a Digital Assistant Based on Holistic User Models forPersonalize...
MyrrorBot: a Digital Assistant Based on Holistic User Models for Personalize...
Cataldo Musto
 
Fairness and Popularity Bias in Recommender Systems: an Empirical Evaluation
Fairness and Popularity Bias in Recommender Systems: an Empirical EvaluationFairness and Popularity Bias in Recommender Systems: an Empirical Evaluation
Fairness and Popularity Bias in Recommender Systems: an Empirical Evaluation
Cataldo Musto
 
Intelligenza Artificiale e Social Media - Monitoraggio della Farnesina e La M...
Intelligenza Artificiale e Social Media - Monitoraggio della Farnesina e La M...Intelligenza Artificiale e Social Media - Monitoraggio della Farnesina e La M...
Intelligenza Artificiale e Social Media - Monitoraggio della Farnesina e La M...
Cataldo Musto
 
Exploring the Effects of Natural Language Justifications in Food Recommender ...
Exploring the Effects of Natural Language Justifications in Food Recommender ...Exploring the Effects of Natural Language Justifications in Food Recommender ...
Exploring the Effects of Natural Language Justifications in Food Recommender ...
Cataldo Musto
 
Towards a Knowledge-aware Food Recommender System Exploiting Holistic User Mo...
Towards a Knowledge-aware Food Recommender System Exploiting Holistic User Mo...Towards a Knowledge-aware Food Recommender System Exploiting Holistic User Mo...
Towards a Knowledge-aware Food Recommender System Exploiting Holistic User Mo...
Cataldo Musto
 
Towards Queryable User Profiles: Introducing Conversational Agents in a Platf...
Towards Queryable User Profiles: Introducing Conversational Agents in a Platf...Towards Queryable User Profiles: Introducing Conversational Agents in a Platf...
Towards Queryable User Profiles: Introducing Conversational Agents in a Platf...
Cataldo Musto
 
Hybrid Semantics aware Recommendations Exploiting Knowledge Graph Embeddings
Hybrid Semantics aware Recommendations Exploiting Knowledge Graph EmbeddingsHybrid Semantics aware Recommendations Exploiting Knowledge Graph Embeddings
Hybrid Semantics aware Recommendations Exploiting Knowledge Graph Embeddings
Cataldo Musto
 
Natural Language Justifications for Recommender Systems Exploiting Text Summa...
Natural Language Justifications for Recommender Systems Exploiting Text Summa...Natural Language Justifications for Recommender Systems Exploiting Text Summa...
Natural Language Justifications for Recommender Systems Exploiting Text Summa...
Cataldo Musto
 
L'IA per l'Empowerment del Cittadino: Hate Map, Myrror, PA Risponde
L'IA per l'Empowerment del Cittadino: Hate Map, Myrror, PA RispondeL'IA per l'Empowerment del Cittadino: Hate Map, Myrror, PA Risponde
L'IA per l'Empowerment del Cittadino: Hate Map, Myrror, PA Risponde
Cataldo Musto
 
Explanation Strategies - Advances in Content-based Recommender System
Explanation Strategies - Advances in Content-based Recommender SystemExplanation Strategies - Advances in Content-based Recommender System
Explanation Strategies - Advances in Content-based Recommender System
Cataldo Musto
 
Justifying Recommendations through Aspect-based Sentiment Analysis of Users R...
Justifying Recommendations through Aspect-based Sentiment Analysis of Users R...Justifying Recommendations through Aspect-based Sentiment Analysis of Users R...
Justifying Recommendations through Aspect-based Sentiment Analysis of Users R...
Cataldo Musto
 
ExpLOD: un framework per la generazione di spiegazioni per recommender system...
ExpLOD: un framework per la generazione di spiegazioni per recommender system...ExpLOD: un framework per la generazione di spiegazioni per recommender system...
ExpLOD: un framework per la generazione di spiegazioni per recommender system...
Cataldo Musto
 
Myrror: una piattaforma per Holistic User Modeling e Quantified Self
Myrror: una piattaforma per Holistic User Modeling e Quantified SelfMyrror: una piattaforma per Holistic User Modeling e Quantified Self
Myrror: una piattaforma per Holistic User Modeling e Quantified Self
Cataldo Musto
 
Semantic Holistic User Modeling for Personalized Access to Digital Content an...
Semantic Holistic User Modeling for Personalized Access to Digital Content an...Semantic Holistic User Modeling for Personalized Access to Digital Content an...
Semantic Holistic User Modeling for Personalized Access to Digital Content an...
Cataldo Musto
 
Holistic User Modeling for Personalized Services in Smart Cities
Holistic User Modeling for Personalized Services in Smart CitiesHolistic User Modeling for Personalized Services in Smart Cities
Holistic User Modeling for Personalized Services in Smart Cities
Cataldo Musto
 
A Framework for Holistic User Modeling Merging Heterogeneous Digital Footprints
A Framework for Holistic User Modeling Merging Heterogeneous Digital FootprintsA Framework for Holistic User Modeling Merging Heterogeneous Digital Footprints
A Framework for Holistic User Modeling Merging Heterogeneous Digital Footprints
Cataldo Musto
 
eHealth, mHealth in Otorinolaringoiatria: innovazioni dirompenti o disastrose?
eHealth, mHealth in Otorinolaringoiatria: innovazioni dirompenti o disastrose?eHealth, mHealth in Otorinolaringoiatria: innovazioni dirompenti o disastrose?
eHealth, mHealth in Otorinolaringoiatria: innovazioni dirompenti o disastrose?
Cataldo Musto
 
Semantics-aware Recommender Systems Exploiting Linked Open Data and Graph-bas...
Semantics-aware Recommender Systems Exploiting Linked Open Data and Graph-bas...Semantics-aware Recommender Systems Exploiting Linked Open Data and Graph-bas...
Semantics-aware Recommender Systems Exploiting Linked Open Data and Graph-bas...
Cataldo Musto
 
Il Linguaggio dell'Odio sui Social Network
Il Linguaggio dell'Odio sui Social NetworkIl Linguaggio dell'Odio sui Social Network
Il Linguaggio dell'Odio sui Social Network
Cataldo Musto
 
Mappare l'Odio - Hate Speech & Social Media
Mappare l'Odio - Hate Speech & Social MediaMappare l'Odio - Hate Speech & Social Media
Mappare l'Odio - Hate Speech & Social Media
Cataldo Musto
 

More from Cataldo Musto (20)

MyrrorBot: a Digital Assistant Based on Holistic User Models for Personalize...
MyrrorBot: a Digital Assistant Based on Holistic User Models forPersonalize...MyrrorBot: a Digital Assistant Based on Holistic User Models forPersonalize...
MyrrorBot: a Digital Assistant Based on Holistic User Models for Personalize...
 
Fairness and Popularity Bias in Recommender Systems: an Empirical Evaluation
Fairness and Popularity Bias in Recommender Systems: an Empirical EvaluationFairness and Popularity Bias in Recommender Systems: an Empirical Evaluation
Fairness and Popularity Bias in Recommender Systems: an Empirical Evaluation
 
Intelligenza Artificiale e Social Media - Monitoraggio della Farnesina e La M...
Intelligenza Artificiale e Social Media - Monitoraggio della Farnesina e La M...Intelligenza Artificiale e Social Media - Monitoraggio della Farnesina e La M...
Intelligenza Artificiale e Social Media - Monitoraggio della Farnesina e La M...
 
Exploring the Effects of Natural Language Justifications in Food Recommender ...
Exploring the Effects of Natural Language Justifications in Food Recommender ...Exploring the Effects of Natural Language Justifications in Food Recommender ...
Exploring the Effects of Natural Language Justifications in Food Recommender ...
 
Towards a Knowledge-aware Food Recommender System Exploiting Holistic User Mo...
Towards a Knowledge-aware Food Recommender System Exploiting Holistic User Mo...Towards a Knowledge-aware Food Recommender System Exploiting Holistic User Mo...
Towards a Knowledge-aware Food Recommender System Exploiting Holistic User Mo...
 
Towards Queryable User Profiles: Introducing Conversational Agents in a Platf...
Towards Queryable User Profiles: Introducing Conversational Agents in a Platf...Towards Queryable User Profiles: Introducing Conversational Agents in a Platf...
Towards Queryable User Profiles: Introducing Conversational Agents in a Platf...
 
Hybrid Semantics aware Recommendations Exploiting Knowledge Graph Embeddings
Hybrid Semantics aware Recommendations Exploiting Knowledge Graph EmbeddingsHybrid Semantics aware Recommendations Exploiting Knowledge Graph Embeddings
Hybrid Semantics aware Recommendations Exploiting Knowledge Graph Embeddings
 
Natural Language Justifications for Recommender Systems Exploiting Text Summa...
Natural Language Justifications for Recommender Systems Exploiting Text Summa...Natural Language Justifications for Recommender Systems Exploiting Text Summa...
Natural Language Justifications for Recommender Systems Exploiting Text Summa...
 
L'IA per l'Empowerment del Cittadino: Hate Map, Myrror, PA Risponde
L'IA per l'Empowerment del Cittadino: Hate Map, Myrror, PA RispondeL'IA per l'Empowerment del Cittadino: Hate Map, Myrror, PA Risponde
L'IA per l'Empowerment del Cittadino: Hate Map, Myrror, PA Risponde
 
Explanation Strategies - Advances in Content-based Recommender System
Explanation Strategies - Advances in Content-based Recommender SystemExplanation Strategies - Advances in Content-based Recommender System
Explanation Strategies - Advances in Content-based Recommender System
 
Justifying Recommendations through Aspect-based Sentiment Analysis of Users R...
Justifying Recommendations through Aspect-based Sentiment Analysis of Users R...Justifying Recommendations through Aspect-based Sentiment Analysis of Users R...
Justifying Recommendations through Aspect-based Sentiment Analysis of Users R...
 
ExpLOD: un framework per la generazione di spiegazioni per recommender system...
ExpLOD: un framework per la generazione di spiegazioni per recommender system...ExpLOD: un framework per la generazione di spiegazioni per recommender system...
ExpLOD: un framework per la generazione di spiegazioni per recommender system...
 
Myrror: una piattaforma per Holistic User Modeling e Quantified Self
Myrror: una piattaforma per Holistic User Modeling e Quantified SelfMyrror: una piattaforma per Holistic User Modeling e Quantified Self
Myrror: una piattaforma per Holistic User Modeling e Quantified Self
 
Semantic Holistic User Modeling for Personalized Access to Digital Content an...
Semantic Holistic User Modeling for Personalized Access to Digital Content an...Semantic Holistic User Modeling for Personalized Access to Digital Content an...
Semantic Holistic User Modeling for Personalized Access to Digital Content an...
 
Holistic User Modeling for Personalized Services in Smart Cities
Holistic User Modeling for Personalized Services in Smart CitiesHolistic User Modeling for Personalized Services in Smart Cities
Holistic User Modeling for Personalized Services in Smart Cities
 
A Framework for Holistic User Modeling Merging Heterogeneous Digital Footprints
A Framework for Holistic User Modeling Merging Heterogeneous Digital FootprintsA Framework for Holistic User Modeling Merging Heterogeneous Digital Footprints
A Framework for Holistic User Modeling Merging Heterogeneous Digital Footprints
 
eHealth, mHealth in Otorinolaringoiatria: innovazioni dirompenti o disastrose?
eHealth, mHealth in Otorinolaringoiatria: innovazioni dirompenti o disastrose?eHealth, mHealth in Otorinolaringoiatria: innovazioni dirompenti o disastrose?
eHealth, mHealth in Otorinolaringoiatria: innovazioni dirompenti o disastrose?
 
Semantics-aware Recommender Systems Exploiting Linked Open Data and Graph-bas...
Semantics-aware Recommender Systems Exploiting Linked Open Data and Graph-bas...Semantics-aware Recommender Systems Exploiting Linked Open Data and Graph-bas...
Semantics-aware Recommender Systems Exploiting Linked Open Data and Graph-bas...
 
Il Linguaggio dell'Odio sui Social Network
Il Linguaggio dell'Odio sui Social NetworkIl Linguaggio dell'Odio sui Social Network
Il Linguaggio dell'Odio sui Social Network
 
Mappare l'Odio - Hate Speech & Social Media
Mappare l'Odio - Hate Speech & Social MediaMappare l'Odio - Hate Speech & Social Media
Mappare l'Odio - Hate Speech & Social Media
 

Recently uploaded

How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...
Product School
 
Welocme to ViralQR, your best QR code generator.
Welocme to ViralQR, your best QR code generator.Welocme to ViralQR, your best QR code generator.
Welocme to ViralQR, your best QR code generator.
ViralQR
 
Assure Contact Center Experiences for Your Customers With ThousandEyes
Assure Contact Center Experiences for Your Customers With ThousandEyesAssure Contact Center Experiences for Your Customers With ThousandEyes
Assure Contact Center Experiences for Your Customers With ThousandEyes
ThousandEyes
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance
 
Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?
Nexer Digital
 
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdfSAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
Peter Spielvogel
 
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
ThousandEyes
 
PCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase TeamPCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase Team
ControlCase
 
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
UiPathCommunity
 
Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
Thijs Feryn
 
PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)
Ralf Eggert
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance
 
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Albert Hoitingh
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
Ana-Maria Mihalceanu
 
By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024
Pierluigi Pugliese
 
Introduction to CHERI technology - Cybersecurity
Introduction to CHERI technology - CybersecurityIntroduction to CHERI technology - Cybersecurity
Introduction to CHERI technology - Cybersecurity
mikeeftimakis1
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
Prayukth K V
 
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
Sri Ambati
 

Recently uploaded (20)

How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...
 
Welocme to ViralQR, your best QR code generator.
Welocme to ViralQR, your best QR code generator.Welocme to ViralQR, your best QR code generator.
Welocme to ViralQR, your best QR code generator.
 
Assure Contact Center Experiences for Your Customers With ThousandEyes
Assure Contact Center Experiences for Your Customers With ThousandEyesAssure Contact Center Experiences for Your Customers With ThousandEyes
Assure Contact Center Experiences for Your Customers With ThousandEyes
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
 
Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?
 
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdfSAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
 
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
 
PCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase TeamPCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase Team
 
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
 
Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
 
PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
 
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
 
By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024
 
Introduction to CHERI technology - Cybersecurity
Introduction to CHERI technology - CybersecurityIntroduction to CHERI technology - Cybersecurity
Introduction to CHERI technology - Cybersecurity
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
 
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
 

Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendation

  • 1. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendation Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis (Università degli Studi di Bari ‘Aldo Moro’, Italy - SWAP Research Group) UMAP 2014 22th Conference on User Modeling, Adaptation and Personalization Aalborg (Denmark) July 8, 2014
  • 2. Content-based Recommender Systems Suggest items similar to those the user liked in the past (I bought Converse should, I’ll continue buying similar sport shoes) Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 2
  • 3. Content-based Recommender Systems Xuser profile items Recommendation are generated by matching the features stored in the user profile with those describing the items to be recommended. Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 3 ♥
  • 4. Content-based Recommender Systems (Some) Limitations Poor Semantic Representation Poor Contextual Modeling Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 4
  • 5. ? Lack of Semantics “I love turkey. It’s my choice for these holidays! Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 5
  • 6. Lack of Contextual Modeling Ashtead? Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 in Aalborg: brewery recommendations 6
  • 7. Lack of Contextual Modeling Many content-based recommendation engines do nothandle contextual information (e.g. user location) 1370km ! far away :-) Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 7
  • 8. contextual eVSM a context-aware content-based recommendation framework based on distributional semantics and entity linking Our contribution Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 8
  • 9. Contextual eVSM Workflow Semantic Content Analyzer Context-aware Profiler Recommender Items User Profiles User Ratings Contextual Data Item Description Context-aware Recommendations Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 9
  • 10. Contextual eVSM 3 main components Semantic ! Content Analyzer! Context-aware ! Profiler! Recommender! Items User Profiles User Ratings Contextual Data Item Description Context-aware Recommendations Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 10
  • 11. ! • Input: items to be recommended (along with their textual description) • Output: semantic representation • Novelty: we exploited • Entity Linking algorithms! • Distributional Semantics Models Contextual eVSM Semantic Content Analyzer Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 11
  • 12. Contextual eVSM • Entity Linking Algorithms! • Input: free text. • items description, in our setting • Output: identification of the most relevant entities mentioned in the text. • We adopted: • tag.me(1) , • DBpedia Spotlight(2) , • Wikipedia Miner(3) Semantic Content Analyzer :: Entity Linking Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 (1) http://tagme.di.unipi.it (2) http://spotlight.dbpedia.org (3) http://wikipedia-miner.cms.waikato.ac.nz 12
  • 13. Contextual eVSM Semantic Content Analyzer :: Entity Linking::Example Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Textual Description (e.g. Wikipedia abstract) Processed Text 13
  • 14. Contextual eVSM Semantic Content Analyzer :: Entity Linking::Example Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Very transparent and human readable content representation Tag.me output 14
  • 15. Contextual eVSM Semantic Content Analyzer :: Entity Linking::Example Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Tag.me output non-trivial NLP tasks (stopwords removal, n-grams identification, named entities recognition and disambiguation) are automatically performed 15 Very transparent and human readable content representation
  • 16. Contextual eVSM Semantic Content Analyzer :: Entity Linking::Example Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Tag.me output Each entity is a reference to a Wikipedia page http://en.wikipedia.org/wiki/The_Wachowskis not a simple textual feature! 16
  • 17. Contextual eVSM Semantic Content Analyzer :: Entity Linking::Example Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 We enriched this entity-based representation ! by exploiting the Wikipedia categories’ tree 17
  • 18. Contextual eVSM Semantic Content Analyzer :: Entity Linking::Representation Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 The final representation of each item is obtained by merging the entities identified in the text with all the Wikipedia categories each entity is linked to. +Entities Wikipedia CategoriesFeatures = 18
  • 19. Contextual eVSM Semantic Content Analyzer :: Entity Linking::Representation Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 The final representation of each item is obtained by merging the entities identified in the text with all the Wikipedia categories each entity is linked to. +Entities Wikipedia CategoriesFeatures = Problem: Even such a rich, transparent and human-readable representation does not handle semantics 19
  • 20. Contextual eVSM Semantic Content Analyzer :: Distributional Semantics Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 “meaning is its use” L.Wittgenstein (Austrian philosopher) 20
  • 21. Contextual eVSM Semantic Content Analyzer :: Distributional Semantics (*) Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 by analyzing large corpora of textual data it is possible to infer information about the usage (about the meaning) of the terms Insight similar meaning co-occurrence co-occurrence co-occurrence co-occurrence (*) Firth, J.R.A synopsis of linguistic theory 1930-1955. In Studies in Linguistic Analysis, pp. 1-32, 1957. 21
  • 22. Contextual eVSM Semantic Content Analyzer :: Distributional Semantics::WordSpace Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 beer wine mojito dog 22 Vector-space representation is based on term co-occurences
  • 23. Contextual eVSM Semantic Content Analyzer :: Distributional Semantics Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 e1 e2 e3 e4 e5 e6 e7 e8 e9 Keanu Reeves ✔ ✔ ✔ ✔ ✔ Al Pacino ✔ ✔ American Writers ✔ ✔ ✔ ✔ Laurence Fishburne ✔ ✔ ✔ ✔ Our Semantic Content Analyzer learns a vector-space item representation based on distributional semantics models 23
  • 24. Contextual eVSM Semantic Content Analyzer :: Distributional Semantics Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 e1 e2 e3 e4 e5 e6 e7 e8 e9 Keanu Reeves ✔ ✔ ✔ ✔ ✔ Al Pacino ✔ ✔ American Writers ✔ ✔ ✔ ✔ Laurence Fishburne ✔ ✔ ✔ ✔ Vector-space Semantic Representation is learnt according to entities co-occurrences in textual descriptions 24
  • 25. Contextual eVSM Semantic Content Analyzer :: Distributional Semantics Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Unexpected connections between entities can be learnt in a total unsupervised way thanks to Distributional Semantics 25
  • 26. Contextual eVSM Semantic Content Analyzer :: Distributional Semantics Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 e1 e2 e3 e4 e5 e6 e7 e8 e9 Keanu Reeves ✔ ✔ ✔ ✔ ✔ Al Pacino ✔ ✔ American Writers ✔ ✔ ✔ ✔ Laurence Fishburne ✔ ✔ ✔ ✔ e.g. Keanu Reeves and Al Pacino both starred in Drama movies 26
  • 27. Contextual eVSM Semantic Content Analyzer :: Distributional Semantics Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 How to exploit Distributional Semantics ! to represent items to be recommended? Question 27
  • 28. Contextual eVSM Semantic Content Analyzer :: Distributional Semantics Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 e1 e2 e3 e4 e5 e6 e7 e8 e9 Keanu Reeves ✔ ✔ ✔ ✔ ✔ Drama ✔ ✔ American Writers ✔ ✔ ✔ ✔ Laurence Fishburne ✔ ✔ ✔ ✔ semantic representation of the items is obtained by combining the vector-space representation of the features which describe them. 28
  • 29. Contextual eVSM Semantic Content Analyzer :: Distributional Semantics Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 e1 e2 e3 e4 e5 e6 e7 e8 e9 Keanu Reeves ✔ ✔ ✔ ✔ ✔ Al Pacino ✔ ✔ American Writers ✔ ✔ ✔ ✔ Laurence Fishburne ✔ ✔ ✔ ✔ Matrix ✔ ✔ ✔ ✔ ✔ ✔ ✔ ✔ 29
  • 30. Contextual eVSM Semantic Content Analyzer :: Distributional Semantics Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Matrix Matrix Revolutions Donnie Darko Up! It is possible to perform similarity calculations between items according to their semantic representation 30
  • 31. ! • Input: • user preferences (ratings) • contextual information • Fixed set of contextual dimensions (company, mood, task, etc.) • Fixed set of values (e.g. company=alone, friends, girlfriend, etc.) • Output: contextual user profiles • Novelty: we introduced a Context-aware Profiling Strategy based on Distributional Models Contextual eVSM Context-aware Profiler Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 31
  • 32. C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj) Contextual eVSM Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Context-aware User Profiler :: Strategy Let’s go straight to the formula 32
  • 33. Contextual eVSM Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Context-aware User Profiler :: Strategy Let u be the target user Let ck be a contextual variable (e.g. task, mood, etc.) Let vj be its value (e.g. task=running, mood=sad, etc.) 33 C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj)
  • 34. Contextual eVSM Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Context-aware User Profiler :: Strategy C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj) A context-aware profile can be learnt by combining two components in a linear fashion 34
  • 35. Contextual eVSM Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Context-aware User Profiler :: Strategy C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj) a non-contextual representation of user preferences a vector space representation of the context itself 35 A context-aware profile can be learnt by combining two components in a linear fashion
  • 36. Contextual eVSM Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Context-aware User Profiler :: Strategy :: WRI(u) C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj) WRI(u) = ∑ di* r(u,i) MAXi=1 |L| NON-CONTEXTUAL USER PREFERENCES 36
  • 37. Contextual eVSM Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Context-aware User Profiler :: Strategy :: WRI(u) C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj) WRI(u) = ∑ di* r(u,i) MAXi=1 |L| items the user liked 37
  • 38. Contextual eVSM Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Context-aware User Profiler :: Strategy :: WRI(u) C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj) WRI(u) = ∑ di* r(u,i) MAXi=1 |L| vector-space representation of the item built by Semantic Content Analyzer 38
  • 39. Contextual eVSM Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Context-aware User Profiler :: Strategy :: WRI(u) C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj) WRI(u) = ∑ di* r(u,i) MAXi=1 |L| normalized rating 39
  • 40. Contextual eVSM Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Context-aware User Profiler :: Strategy :: context(u,ck,vj) C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj) context(u,ck,vj) = ∑ di* r(u,i,ck,vj) MAXi=1 |L(ck,vj)| Vector-space representation of the context 40
  • 41. Contextual eVSM Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj) context(u,ck,vj) = ∑ di* r(u,i,ck,vj) MAXi=1 |L(ck,vj)| items the user liked in that specific context Context-aware User Profiler :: Strategy :: context(u,ck,vj) 41
  • 42. r(u,i,ck,vj) Contextual eVSM Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj) context(u,ck,vj) = ∑ di* MAXi=1 |L(ck,vj)| vector space representation of the item Context-aware User Profiler :: Strategy :: context(u,ck,vj) 42
  • 43. Contextual eVSM Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj) context(u,ck,vj) = ∑ di* r(u,i,ck,vj) MAXi=1 |L(ck,vj)| normalized rating in that specific context Context-aware User Profiler :: Strategy :: context(u,ck,vj) 43
  • 44. Contextual eVSM Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Context-aware User Profiler :: Strategy C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj) Ratio: context is just a factor which can influence user’s perception of an item 44
  • 45. Contextual eVSM Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Context-aware User Profiler :: Strategy if the user did not express any preference in that specific contextual setting, context(u,ck,vj) = 0 ! —> non contextual recommendation C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj) Ratio: context is just a factor which can influence user’s perception of an item 45 X
  • 46. Contextual eVSM Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Context-aware User Profiler :: Strategy Otherwise parameter α is exploited to tune a specific component of the formula Ratio: context is just a factor which can influence user’s perception of an item 46 C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj)
  • 47. Contextual eVSM Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Context-aware User Profiler :: How do we come to this formula? C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj) 47
  • 48. C-WRI(u,ck,vj) = α * WRI(u) + (1-α) * context(u,ck,vj) Contextual eVSM Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Context-aware User Profiler :: How do we come to this formula? Insight: it exists a set of terms that is more descriptive of items relevant in that specific context for a romantic dinner, e.g. candlelight, seaview, violin 48 e.g. task = dinner, company=girlfriend
  • 49. Context is represented on the ground of the items the user liked in that specific contextual setting Contextual eVSM Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Context-aware User Profiler :: Our formula inherits this insight 49 r(u,i,ck,vj) MAXi=1 |L(ck,vj)| context(u,ck,vj) = ∑ di*
  • 50. Context is represented on the ground of the items the user liked in that specific contextual setting Contextual eVSM Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 50 r(u,i,ck,vj) MAX Items are represented on the ground of the co-occurrences between entities i=1 |L(ck,vj)| context(u,ck,vj) = ∑ di* Context-aware User Profiler :: Our formula inherits this insight
  • 51. Context is represented on the ground of the items the user liked in that specific contextual setting Contextual eVSM Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 51 r(u,i,ck,vj) MAX Items are represented on the ground of the co-occurrences between entities i=1 |L(ck,vj)| context(u,ck,vj) = ∑ di* the resulting representation of the context is such that a bigger weight is given to the entities which typically occur in the description of the items relevant in that specific context Context-aware User Profiler :: Our formula inherits this insight
  • 52. context(u,ck,vj) = ∑ di* Contextual eVSM Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 52 r(u,i,ck,vj) MAX Thanks to Distributional Semantics Models it is possible to build a vector-space representation of the context which emphasize the importance of those terms, since they are more used (—> more important) in that specific contextual setting. i=1 |L(ck,vj)| Context-aware User Profiler :: Our formula inherits this insight
  • 53. Contextual eVSM Recommendation step Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Skyfall WRI(u) Austin Powers Up! The goal of our context-aware profiling strategy is to perturb the representation of user preferences and to provide him with context-aware recommendations 53 non-contextual preferences
  • 54. Contextual eVSM Recommendation step Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Skyfall C-WRI(u) Austin Powers Up! The goal of our context-aware profiling strategy is to perturb the representation of user preferences and to provide him with context-aware recommendations 54 contextual preferences (e.g. company = friends)
  • 55. Experimental Evaluation Research Hypothesis Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 55 1. Does C-eVSM outperform its non-contextual counterpart? 2. Does the novel representation based on entity linking and distributional semantics outperform a simple keyword- based one? 3. How does our model perform with respect to the current literature?
  • 56. Experimental Evaluation Description of the dataset Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 56 • Movie recommendation! • Subset of IMDB data • 202 movies (textual features crawled from Wikipedia) • 62 users and 1457 ratings! • 4 contextual dimensions! • TIME (weekend, weekday) • PLACE (theather, home) • COMPANION (alone, friends, boyfriend, family) • MOVIE-RELATED (release week or not)
  • 57. Experimental Evaluation Design of the Experiment Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 57 • Dataset and experimental settings replicate Adomavicius’ experiment (*)! • Evaluation over 9 different contextual settings! • Home, Friends, Non-release, Weekend, Weekday, GBFriends, TheatherWeekend and TheatherFriends • Metric: F1-Measure • Experimental protocol: bootstrapping! • 29/30th of the data as training • 1/30th as test • Randomly generated, 500 runs (*) G.Adomavicius et al. , Incorporating contextual information in recommender systems using a multi-dimensional approach.ACM Trans. Inf. Systems, 2005
  • 58. Experimental Evaluation eVSM configurations Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 58 • Non-contextual baseline: eVSM! • WRI profiling strategy • WQN profiling strategy • Context-aware framework: C- eVSM! • C-WRI profiling strategy • C-WQN profiling strategy • Three values for parameter α! • 0.2 , 0.5, 0.8 8 configurations for each run
  • 59. Experimental Evaluation eVSM configurations Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 59 • Non-contextual baseline: eVSM! • WRI profiling strategy • WQN profiling strategy • Context-aware framework: C- eVSM! • C-WRI profiling strategy • C-WQN profiling strategy • Three values for parameter α! • 0.2 , 0.5, 0.8 • WQN! • Alternative profiling strategy (*) • Models negative user feedbacks as well • Combines positive and negative preferences by means of a Quantum Negation (**) Operator (*) C. Musto, G. Semeraro, P. Lops, and M. de Gemmis. Random indexing and 
 negative user preferences for enhancing content-based recommender systems. In EC-Web 2011, volume 85 of LNBIP, pages 270–281. 2011. (**) D. Widdows. Orthogonal negation in vector spaces for modelling word- meanings and document retrieval. In ACL, pages 136–143, 2003.
  • 60. Experiment 1 Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 60 Comparison of C-eVSM vs eVSM (keyword-based)
  • 61. Experiment 1 Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 61 Selection of Results :: HOME segment WRI C-WRI-0.2 C-WRI-0.5 C-WRI-0.8 WQN C-WQN-0.2 C-WQN-0.5 C-WQN-0.8 45 48,75 52,5 56,25 60 58,8 57,82 54,81 53,62 50,6 48,23 46,62 47,62 contextual eVSM improves the F1 measure
  • 62. Experiment 1 Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 62 Selection of Results :: HOME segment WRI C-WRI-0.2 C-WRI-0.5 C-WRI-0.8 WQN C-WQN-0.2 C-WQN-0.5 C-WQN-0.8 45 48,75 52,5 56,25 60 58,8 57,82 54,81 53,62 50,6 48,23 46,62 47,62 contextual eVSM improves the F1 measure paired t-test (p<0.05) baseline baseline
  • 63. Experiment 1 Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 63 Selection of Results :: HOME segment WRI C-WRI-0.2 C-WRI-0.5 C-WRI-0.8 WQN C-WQN-0.2 C-WQN-0.5 C-WQN-0.8 45 48,75 52,5 56,25 60 58,8 57,82 54,81 53,62 50,6 48,23 46,62 47,62 α=0.8 is better than α=0.5
  • 64. WRI C-WRI-0.2 C-WRI-0.5 C-WRI-0.8 WQN C-WQN-0.2 C-WQN-0.5 C-WQN-0.8 42,0 45,3 48,5 51,8 55,0 54,39 50,04 45,93 53,18 50,11 50,54 44,91 49,43 Experiment 1 Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 64 Selection of Results :: FRIENDS segment Similar outcomes: C-eVSM outperforms eVSM paired t-test (p<0.05)
  • 65. WRI C-WRI-0.2 C-WRI-0.5 C-WRI-0.8 WQN C-WQN-0.2 C-WQN-0.5 C-WQN-0.8 42,0 45,3 48,5 51,8 55,0 54,39 50,04 45,93 53,18 50,11 50,54 44,91 49,43 Experiment 1 Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 65 Selection of Results :: FRIENDS segment α=0.2 does not improve F1-measure
  • 66. WRI C-WRI-0.2 C-WRI-0.5 C-WRI-0.8 WQN C-WQN-0.2 C-WQN-0.5 C-WQN-0.8 42,0 45,8 49,5 53,3 57,0 56,78 52,55 48,67 55,94 52,18 49,05 48,24 48,95 Experiment 1 Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 66 Selection of Results :: NON-RELEASE segment C-WQN with α=0.8 is typically the best-performing configuration paired t-test (p<0.05)
  • 67. WRI C-WRI-0.2 C-WRI-0.5 C-WRI-0.8 WQN C-WQN-0.2 C-WQN-0.5 C-WQN-0.8 42,0 45,8 49,5 53,3 57,0 56,78 52,55 48,67 55,94 52,18 49,05 48,24 48,95 Experiment 1 Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 67 Selection of Results :: NON-RELEASE segment Outcome: context has just to slightly influence user preferences
  • 68. Experiment 1 Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 68 Outcomes • Contextual eVSM outperforms eVSM • 8 segments out of 9 • Little statistical significance • Negation is useful when dataset is well-balanced • Higher α values lead to a better F1 • Best-performing configurations are C-WQN-0.8 (4 times), C-WRI-0.8 (1 times), C-WRI-0.5 (3 times)
  • 69. Experiment 2 Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 69 Comparison of entity-based vs keyword-based content representation
  • 70. Experiment 2 Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 70 WRI C-WRI-0.2 C-WRI-0.5 C-WRI-0.8 WQN C-WQN-0.2 C-WQN-0.5 C-WQN-0.8 40,0 47,5 55,0 62,5 70,0 61,30 61,96 54,81 57,53 56,75 56,38 46,62 56,13 58,80 57,82 53,37 53,62 50,60 48,23 44,56 47,62 Keywords Entities Selection of Results :: HOME segment Semantic representation improves F1 in all the configurations
  • 71. Experiment 2 Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 71 Selection of Results :: HOME segment Gaps are significant in 5 out of 8 configurations WRI C-WRI-0.2 C-WRI-0.5 C-WRI-0.8 WQN C-WQN-0.2 C-WQN-0.5 C-WQN-0.8 40,0 47,5 55,0 62,5 70,0 61,3 61,96 54,81 57,53 56,75 56,38 46,62 56,13 58,80 57,82 53,37 53,62 50,60 48,23 44,56 47,62 Keywords Entities
  • 72. WRI C-WRI-0.2 C-WRI-0.5 C-WRI-0.8 WQN C-WQN-0.2 C-WQN-0.5 C-WQN-0.8 40,0 47,5 55,0 62,5 70,0 61,3 61,96 54,81 57,53 56,75 56,38 46,62 56,13 58,80 57,82 53,37 53,62 50,60 48,23 44,56 47,62 Keywords Entities Experiment 2 Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 72 Selection of Results :: HOME segment Again, higher α values lead to the best F1-measure scores
  • 73. WRI C-WRI-0.2 C-WRI-0.5 C-WRI-0.8 WQN C-WQN-0.2 C-WQN-0.5 C-WQN-0.8 43,0 48,5 54,0 59,5 65,0 58,37 57,2 52,82 58,25 55,68 56,24 49,19 56,17 54,39 50,04 45,93 53,18 50,11 50,54 44,91 49,43 Keywords Entities Experiment 2 73 Selection of Results :: FRIEND segment Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 +6,42%improvement, gap always significant
  • 74. WRI C-WRI-0.2 C-WRI-0.5 C-WRI-0.8 WQN C-WQN-0.2 C-WQN-0.5 C-WQN-0.8 43,0 48,5 54,0 59,5 65,0 58,37 57,2 52,82 58,25 55,68 56,24 49,19 56,17 54,39 50,04 45,93 53,18 50,11 50,54 44,91 49,43 Keywords Entities Experiment 2 74 Selection of Results :: FRIEND segment Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Negation+ α Higher values ➝ best configuration
  • 75. WRI C-WRI-0.2 C-WRI-0.5 C-WRI-0.8 WQN C-WQN-0.2 C-WQN-0.5 C-WQN-0.8 43,0 48,5 54,0 59,5 65,0 62,16 57,81 54,72 56,45 58,11 57,21 55,82 56,34 52,64 51,40 46,65 50,71 52,87 53,95 52,79 50,91 Keywords Entities Experiment 2 75 Selection of Results :: THEATER segment Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Best perfoming segment: +6,49% improvement over keywords
  • 76. WRI C-WRI-0.2 C-WRI-0.5 C-WRI-0.8 WQN C-WQN-0.2 C-WQN-0.5 C-WQN-0.8 43,0 48,5 54,0 59,5 65,0 62,16 57,81 54,72 56,45 58,11 57,21 55,82 56,34 52,64 51,40 46,65 50,71 52,87 53,95 52,79 50,91 Keywords Entities Experiment 2 76 Selection of Results :: THEATER segment Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 C-WQN is the best perfoming configuration: +9,52%
  • 77. Experiment 2 Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 77 Outcomes • Novel semantic representation outperforms the keyword-based one • 7 segments out of 9 • +4% on average, eanging from +1,34% to +6,49% • Important gaps in terms of F1-measure • Entity-based outperforms keywords in 65 segments out of 90 (72%) • Statistically significant gap in 52 out of 90 of the comparisons (58%) • Negation and higher α values lead to a better F1 • Best-performing configurations are C-WQN-0.8 (3 times), C-WQN-0.5 (2 times), C-WRI-0.5 (2 times)
  • 78. Experiment 3 Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 78 Comparison to context-aware CF algorithm(*) (*) G.Adomavicius et al. , Incorporating contextual information in recommender systems using a multi- dimensional approach.ACM Trans. Inf. Systems, 2005
  • 79. Home Friends Weekend Theater Nonrelease Weekday GBFriends Theater-Weekend Theater-Friends 35,0 43,8 52,5 61,3 70,0 60,7 64,1 48 37,9 43,2 60,8 54,2 48,2 39,19 55,96 54,95 50,72 48,02 57,01 61,16 60,39 58,37 61,96 c-eVSM CACF Experiment 3 79Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Comparison to context-aware CF algorithm Contextual eVSM overcomes CACF in 7 segments out of 9 ✔
  • 80. Home Friends Weekend Theater Nonrelease Weekday GBFriends Theater-Weekend Theater-Friends 35,0 43,8 52,5 61,3 70,0 60,7 64,1 48 37,9 43,2 60,8 54,2 48,2 39,19 55,96 54,95 50,72 48,02 57,01 61,16 60,39 58,37 61,96 c-eVSM CACF Experiment 3 80Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Comparison to context-aware CF algorithm Gap is statistically significant in 5 segments out of 7
  • 81. Recap 81Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
  • 82. Recap 82Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Contextual eVSM: context-aware recommendation framework Content Representation based on Distributional Semantics and Entity Linking Profile Learning based on a perturbation of non-contextual preferences with a semantic representation of the context! Experimental session confirmed the effectiveness of the framework as well as of the novel semantic representation! Framework overcomes a context-aware collaborative filtering baseline
  • 83. Future Research 83Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014
  • 84. Future Research 84Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis. Combining Distributional Semantics and Entity Linking for Context-aware Content-based Recommendations. UMAP 2014, Aalborg (Denmark), July 8, 2014 Evaluation against different datasets and stronger baselines; Exploitation of Linked Data and Open Knowledge Sources for content representation; Evaluation of Novelty, Diversity and Serendipity of the Recommendations;