Monetizing User Activity on Social Networks - Challenges and Experiences, 2009 IEEE/WIC/ACM International Conference on Web Intelligence, Sep 15-18 2009
1. Meena
Nagarajan,
Amit
P.
Sheth
KNO.E.SIS
Center
Wright
State
University
M.
Nagarajan,
K.
Baid,
A.
P.
Sheth,
and
S.
Wang,
"Monetizing
User
Activity
on
Social
Networks
-‐
Challenges
and
Experiences“,
2009
IEEE/WIC/ACM
International
Conference
on
Web
Intelligence,
Milan,
Italy
2. On
social
networks
Use
case
for
this
talk
Targeted
content
=
content-‐based
advertisements
Target
=
user
profiles
Content-‐based
advertisements
CBAs
Well-‐known
monetization
model
for
online
content
5. Interests
do
not
translate
to
purchase
intents
Interests
are
often
outdated..
Intents
are
rarely
stated
on
a
profile..
Cases
that
work
New
store
openings,
sales
Highly
demographic-‐targeted
ads
8. Non-‐trivial
Non-‐policed
content
▪ Brand
image,
Unfavorable
sentiments1
People
are
there
to
network
▪ User
attention
to
ads
is
not
guaranteed
Informal,
casual
nature
of
content
▪ People
are
sharing
experiences
and
events
▪ Main
message
overloaded
with
off
topic
content
I
NEED
HELP
WITH
SONY
VEGAS
PRO
8!!
Ugh
and
i
have
a
video
project
due
tomorrow
for
merrill
lynch
:((
all
i
need
to
do
is
simple:
Extract
several
scenes
from
a
clip,
insert
captions,
transitions
and
thats
it.
really.
omgg
i
cant
figure
out
anything!!
help!!
and
i
got
food
poisoning
from
eggs.
its
not
fun.
Pleasssse,
help?
:(
1Learning
from
Multi-‐topic
Web
Documents
for
Contextual
Advertisement,
Zhang,
Y.,
Surendran,
A.
C.,
Platt,
J.
C.,
and
Narasimhan,
M.
,
KDD
2008
9. Cultural
Entities
HOW
Word
Usages
in
self-‐
presentation
WHY
Slang
sentiments
WHAT
Intentions
10. Identifying
intents
behind
user
posts
on
social
networks
Content
with
monetization
potential
Identifying
keywords
for
advertizing
in
user-‐
generated
content
Interpersonal
communication
&
off-‐topic
chatter
11. User
studies
Hard
to
compare
activity
based
ads
to
s.o.t.a
Impressions
to
Clickthroughs
How
well
are
we
able
to
identify
monetizable
posts
How
targeted
are
ads
generated
using
our
keywords
vs.
entire
user
generated
content
13. Scribe
Intent
not
same
as
Web
Search
Intent1
People
write
sentences,
not
keywords
or
phrases
Presence
of
a
keyword
does
not
imply
navigational
/
transactional
intents
‘am
thinking
of
getting
X’
(transactional)
‘i
like
my
new
X’
(information
sharing)
‘what
do
you
think
about
X’
(information
seeking)
1B.
J.
Jansen,
D.
L.
Booth,
and
A.
Spink,
“Determining
the
informational,
navigational,
and
transactional
intent
of
web
queries,”
Inf.
Process.
Manage.,
vol.
44,
no.
3,
2008.
14. Action
patterns
surrounding
an
entity
How
questions
are
asked
and
not
topic
words
that
indicate
what
the
question
is
about
“where
can
I
find
a
chotto
psp
cam”
User
post
also
has
an
entity
15. Set
of
user
posts
from
SNSs
Not
annotated
for
presence
or
absence
of
any
intent
16. Generate
a
universal
set
of
n-‐gram
patterns;
freq
>
f
S
=
set
of
all
4-‐grams;
freq
>
3
17. Generate
set
of
candidate
patterns
from
seed
words
(why,when,where,how,what)
Sc
=
all
4-‐grams
in
S
that
extract
seed
words
18. User
picks
10
seed
patterns
from
Sc
Sis
=
‘does
anyone
know
how’,
‘where
do
i
find’,
‘someone
tell
me
where’….
19. Sc
=
all
4-‐grams
in
S
that
Sis
=
‘does
anyone
know
how’,
‘where
extract
seed
words
do
i
find’,
‘someone
tell
me
where’….
Gradually
expand
Sis
by
adding
Information
Seeking
patterns
from
Sc
20. Sis
=
‘does
anyone
know
how’,
‘where
do
i
find’,
‘someone
tell
me
where’….
For
every
pis
in
Sis
generate
set
of
filler
patterns
21. ‘.*
anyone
know
how’
‘does
anyone
.*
how’
‘does
.*
know
how’
‘does
anyone
know
.*’
‘does
anyone
know
how’
Look
for
patterns
in
Sc
-‐ Functional
compatibility
of
filler
-‐ words
used
in
similar
semantic
contexts
-‐
Empirical
support
for
filler
22. Functional
properties
/
communicative
functions
of
words
From
a
subset
of
LIWC1
cognitive
mechanical
(e.g.,
if,
whether,
wondering,
find)
▪ ‘I
am
thinking
about
getting
X’
adverbs
(e.g.,
how,
somehow,
where)
impersonal
pronouns
(e.g.,
someone,
anybody,
whichever)
▪ ‘Someone
tell
me
where
can
I
find
X’
1Linguistic
Inquiry
Word
Count,LIWC,
http://liwc.net
24. Over
iterations,
single-‐word
substitutions,
functional
usage
and
empirical
support
conservatively
expands
Sis
Infusing
new
patterns
and
seed
words
Stopping
conditions
25. does anyone know how no idea how to
anyone know how to someone tell me how
i dont know what have no clue what
know where i can does anyone know if
tell me how to i dont know if
i dont know how know if i can
anyone know where i anyone know if i
does anyone know where im not sure if
does anyone know what i was wondering if
anybody know how to idea what you are
anyone know how i let me know how
im not sure what and i dont know
does anybody know how now i dont know
does anyone know why but i dont really
i was wondering how was wondering if someone
does anyone know when would like to see
tell me what to see what i can
im not sure how anyone have any idea
i was wondering what wondering if someone could
was wondering how i
i do not want
26. Information
Seeking
patterns
generated
offline
Information
seeking
intent
score
of
a
post
Extract
and
compare
patterns
in
posts
with
extracted
patterns
Transactional
intent
score
of
a
post
▪ LIWC
‘Money’
dictionary
▪ 173
words
and
word
forms
indicative
of
transactions,
e.g.,
trade,
deal,
buy,
sell,
worth,
price
etc.
27. Training
corpus
8000
user
posts
▪ MySpace
Computers,
Electronics,
Gadgets
forum
309
unique
new
patterns,
263
unambiguous
Testing
patterns
for
recall
‘To
buy’
Marketplace
–
average
81
%
29. Identifying
keywords
in
monetizable
posts
Plethora
of
work
in
this
space
Off-‐topic
noise
removal
is
our
focus
I
NEED
HELP
WITH
SONY
VEGAS
PRO
8!!
Ugh
and
i
have
a
video
project
due
tomorrow
for
merrill
lynch
:((
all
i
need
to
do
is
simple:
Extract
several
scenes
from
a
clip,
insert
captions,
transitions
and
thats
it.
really.
omgg
i
cant
figure
out
anything!!
help!!
and
i
got
food
poisoning
from
eggs.
its
not
fun.
Pleasssse,
help?
:(
30. Topical
hints
C1
-‐
['camcorder']
Keywords
in
post
C2
-‐
['electronics
forum',
'hd',
'camcorder',
'somethin',
'ive',
'canon',
'little
camera',
'canon
hv20',
'cameras',
'offtopic']
Move
strongly
related
keywords
from
C2
to
C1
one-‐by-‐one
Relatedness
determined
using
information
gain
Using
the
Web
as
a
corpus,
domain
independent
33. Keywords
from
60
monetizable
user
posts
Monetizable
intent,
at
least
3
keywords
in
content
45
MySpace
Forums,
15
Facebook
Marketplace,
30
graduate
students
10
sets
of
6
posts
each
Each
set
evaluated
by
3
randomly
selected
users
Monetizable
intents?
All
60
posts
voted
as
unambiguously
information
seeking
in
intent
34. Google
AdSense
ads
for
user
post
vs.
extracted
topical
keywords
35. Choose
relevant
Ad
Impressions
VW
6
disc
CD
changer
I
need
one
thats
compatible
with
a
2000
golf
most
are
sold
from
years
1998-‐2004if
anyone
has
one
[or
can
get
one]
PLEASE
let
me
know!
36. Users
picked
ads
relevant
to
the
post
At
least
50%
inter-‐evaluator
agreement
For
the
60
posts
Total
of
144
ad
impressions
17%
of
ads
picked
as
relevant
For
the
topical
keywords
Total
of
162
ad
impressions
40%
of
ads
picked
as
relevant
37. User’s
profile
information
Interests,
hobbies,
tv
shows..
Non-‐demographic
information
Submit
a
post
Looking
to
buy
and
why
(induced
noise)
Ads
that
generate
interest,
captured
attention
38. Using
profile
ads
Total
of
56
ad
impressions
7%
of
ads
generated
interest
Using
authored
posts
Total
of
56
ad
impressions
43%
of
ads
generated
interest
Using
topical
keywords
from
authored
posts
Total
of
59
ad
impressions
59%
of
ads
generated
interest
39. User
studies
small
and
preliminary,
clearly
suggest
Monetization
potential
in
user
activity
Improvement
for
Ad
programs
in
terms
of
relevant
impressions
Evaluations
based
on
forum,
marketplace
Verbose
content
Status
updates,
notes,
community
and
event
memberships…
One
size
may
not
fit
all
40. A
world
between
relevant
impressions
and
clickthroughs
Objectionable
content,
vocabulary
impedance,
Ad
placement,
network
behavior
In
a
pipeline
of
other
community
efforts
No
profile
information
taken
into
account
Cannot
custom
send
information
to
Google
AdSense
41. Keywords
to
Ad
Impressions
Google
Adsense
like
web
service
Monetization
potential
of
a
keyword
on
the
Web
not
the
same
on
a
social
n/w?
Ranking
keywords
in
user
post
We
are
building
an
F8
app
Collaboration
for
clickthrough
data