SlideShare a Scribd company logo
1 of 26
ENTER 2016 Research Track Slide Number 1
Contextual Information Elicitation in
Travel Recommender Systems
Matthias Braunhofer and Francesco Ricci
Free University of Bozen - Bolzano, Italy
{mbraunhofer,fricci}@unibz.it
http://www.inf.unibz.it
ENTER 2016 Research Track Slide Number 2
Agenda
• Introduction
• Related Work
• Selective Context Acquisition
• Experimental Evaluation and Results
• Conclusions
ENTER 2016 Research Track Slide Number 4
Context-Aware
Recommender Systems (CARSs)
• CARSs provide better recommendations by
incorporating contextual information (e.g., time
and weather) into the recommendation process
STS (South Tyrol Suggests)
ENTER 2016 Research Track Slide Number 5
Context Acquisition
Problem of CARSs
• How to identify and acquire the truly relevant
contextual factors that influence the user
preferences and decision making process?
ENTER 2016 Research Track Slide Number 6
STS w/o Selective
Context Acquisition
We can’t elicit the conditions for all the available
contextual factors when the user rates a POI.
ENTER 2016 Research Track Slide Number 7
STS w/ Selective
Context Acquisition
Rather, we must elicit the conditions of a small
subset of most important contextual factors.
ENTER 2016 Research Track Slide Number 8
Agenda
ENTER 2016 Research Track Slide Number 9
Context Acquisition
Problem in Commercial Systems
• Numerous commercial systems in the tourism
domain face the context acquisition problem
TripAdvisor Foursquare
ENTER 2016 Research Track Slide Number 10
A Priori Context Selection
• Web survey in which
users evaluate the
influence of contextual
conditions on POI
categories
• Allows to identify the
relevant factors before
collecting ratings
(Baltrunas et al., 2012)
ENTER 2016 Research Track Slide Number 11
A Posteriori Context Selection
• Several statistic-based
methods for detecting
the relevant context
after collecting ratings
• Results show a
significant difference in
prediction of ratings in
relevant vs. irrelevant
context (Odić et al., 2013)
ENTER 2016 Research Track Slide Number 12
Agenda
ENTER 2016 Research Track Slide Number 13
Parsimonious and
Adaptive Context Acquisition
• Main idea: for each user-item pair (u, i), identify
the contextual factors that when acquired with
u’s rating for i improve most the long term
performance of the recommender
– Heuristic: acquire the contextual factors that have the
largest impact on rating prediction
• Challenge: how to quantify these impacts?
ENTER 2016 Research Track Slide Number 14
CARS Prediction Model
• We use a new variant of Context-Aware Matrix
Factorization (CAMF) (Baltrunas et al., 2011) that treats
contextual conditions similarly to either item or
user attributes
ˆruic1,...,ck
= (qi + xa )T
(pu + yb )+ ri
b∈A(u)∪C(u)
∑ + bu
a∈A(i)∪C(i)
∑
Latent vector of item i Latent vector of user u
Latent vectors of
conventional (e.g., genre)
and contextual item
attributes (e.g., weather)
Avg. rating for item i
Bias of user uLatent vectors of
conventional (e.g., age)
and contextual user
attributes (e.g., mood)
ENTER 2016 Research Track Slide Number 15
Largest Deviation
• Given (u, i), it computes a relevance score for
each contextual factor Cj by first measuring the
“impact” of each contextual condition cj C∈ j:
• Finally, it computes for each factor the average of
these deviation scores, and selects the contextual
factors with the largest average scores
ˆwuicj
= fcj
ˆruicj
− ˆrui
Normalized freq. of cj
Rating prediction when cj holds
Predicted context-free rating
ENTER 2016 Research Track Slide Number 16
Illustrative Example
• Let ȓAliceSkiingSunny = 5, ȓAliceSkiing = 3.5 & fSunny = 0.2. Then, the
impact of the “Sunny” condition is:
– ŵAliceSkiingSunny = 0.2 · |5 - 3.5| = 0.3
• Let ŵAliceSkiingCloudy= 0.2, ŵAliceSkiingRainy= 0.3 &
ŵAliceSkiingSnowy= 0.1, the impacts of the other weather
conditions. Then, the overall impact of the
“Weather” factor is:
– (0.3 + 0.2 + 0.3 + 0.1) ÷ 5 = 0.18
ENTER 2016 Research Track Slide Number 17
Agenda
ENTER 2016 Research Track Slide Number 18
Datasets
Dataset STS TripAdvisor
Rating scale 1-5 1-5
Ratings 2,534 4,147
Users 325 3,916
Items 249 569
Contextual factors 14 3
Contextual conditions 57 31
Avg. # of factors known for
each rating
1.49 3
User attributes 7 2
Item attributes 1 12
In STS when a user rates
a POI she commonly
specifies at most 4 out
of the 14 factors!
In STS when a user rates
a POI she commonly
specifies at most 4 out
of the 14 factors!
ENTER 2016 Research Track Slide Number 19
Evaluation Procedure: Overview
• Repeated random sampling (20 times):
– Randomly partition the ratings into 3 subsets
– For each user-item pair (u, i) in the candidate set, compute the N most
relevant contextual factors and transfer the corresponding rating and
context information ruic in the candidate set to the training set as ruic’ with
c’ c containing the conditions for these factors, if any⊆
– Measure prediction accuracy (MAE) and ranking quality (Precision) on
testing set, after training the prediction model on extended training set
– Repeat
Training set (25%) Candidate set (50%) Testing set (25%)
ENTER 2016 Research Track Slide Number 20
user-item pair
Evaluation Procedure: Example
(Alice, Skiing)
Season and Weather
rAlice Skiing Winter, Sunny, Warm, Morning = 5
rAlice Skiing Winter, Sunny = 5
top two contextual factors
rating in candidate set
rating transferred to training set
+
+
=
ENTER 2016 Research Track Slide Number 21
Baseline Methods for Evaluation
• Mutual Information: given a user-item pair (u,i),
computes the relevance for a contextual factor Cj
as the mutual information between ratings for
items belonging to i’s category (Baltrunas et al., 2012)
• Freeman-Halton Test: calculates the relevance of
Cj using the Freeman-Halton test (Odić et al., 2013)
• mRMR: ranks each Cj according to its relevance to
the rating variable and redundancy to other
contextual factors (Peng et al., 2005)
ENTER 2016 Research Track Slide Number 22
Evaluation Results:
Prediction Accuracy
ENTER 2016 Research Track Slide Number 23
Evaluation Results:
Ranking Quality
ENTER 2016 Research Track Slide Number 24
Evaluation Results:
# of Acquired Conditions
ENTER 2016 Research Track Slide Number 25
Agenda
ENTER 2016 Research Track Slide Number 26
Conclusions
• Using Largest Deviation, we know that we can ask
only the contextual factors C1, C2 and C3 when we
ask user u to rate item i
ENTER 2016 Research Track Slide Number 29
Questions?
Thank you.

More Related Content

What's hot

THE IMPACT OF ELECTRONIC WORD OF MOUTH ON TOURISTS’ INTENTION OF DESTINATION ...
THE IMPACT OF ELECTRONIC WORD OF MOUTH ON TOURISTS’ INTENTION OF DESTINATION ...THE IMPACT OF ELECTRONIC WORD OF MOUTH ON TOURISTS’ INTENTION OF DESTINATION ...
THE IMPACT OF ELECTRONIC WORD OF MOUTH ON TOURISTS’ INTENTION OF DESTINATION ...Pubudu Weerasinghe
 
Predictability of popularity on online social media: Gaps between prediction ...
Predictability of popularity on online social media: Gaps between prediction ...Predictability of popularity on online social media: Gaps between prediction ...
Predictability of popularity on online social media: Gaps between prediction ...Amit Sharma
 
How NOT to Aggregrate Polling Data
How NOT to Aggregrate Polling DataHow NOT to Aggregrate Polling Data
How NOT to Aggregrate Polling DataDataCards
 
Essential econometrics for data scientists
Essential econometrics for data scientistsEssential econometrics for data scientists
Essential econometrics for data scientistsBenjamin Skrainka
 
Context-Aware Recommender Systems for Mobile Devices
Context-Aware Recommender Systems for Mobile DevicesContext-Aware Recommender Systems for Mobile Devices
Context-Aware Recommender Systems for Mobile DevicesMatthias Braunhofer
 
An online evaluation of explicit feedback mechanisms for recommender systems
An online evaluation of explicit feedback mechanisms for recommender systemsAn online evaluation of explicit feedback mechanisms for recommender systems
An online evaluation of explicit feedback mechanisms for recommender systemsSimon Dooms
 

What's hot (12)

THE IMPACT OF ELECTRONIC WORD OF MOUTH ON TOURISTS’ INTENTION OF DESTINATION ...
THE IMPACT OF ELECTRONIC WORD OF MOUTH ON TOURISTS’ INTENTION OF DESTINATION ...THE IMPACT OF ELECTRONIC WORD OF MOUTH ON TOURISTS’ INTENTION OF DESTINATION ...
THE IMPACT OF ELECTRONIC WORD OF MOUTH ON TOURISTS’ INTENTION OF DESTINATION ...
 
Predictability of popularity on online social media: Gaps between prediction ...
Predictability of popularity on online social media: Gaps between prediction ...Predictability of popularity on online social media: Gaps between prediction ...
Predictability of popularity on online social media: Gaps between prediction ...
 
Smart Glasses Adoption in Smart Tourism Destination: A Conceptual Model
Smart Glasses Adoption in Smart Tourism Destination: A Conceptual ModelSmart Glasses Adoption in Smart Tourism Destination: A Conceptual Model
Smart Glasses Adoption in Smart Tourism Destination: A Conceptual Model
 
Channels for Searching Hotel and Travel Information
Channels for Searching Hotel and Travel InformationChannels for Searching Hotel and Travel Information
Channels for Searching Hotel and Travel Information
 
NFC-Enabled City Maps Measuring their Perceived Value
NFC-Enabled City Maps Measuring their Perceived ValueNFC-Enabled City Maps Measuring their Perceived Value
NFC-Enabled City Maps Measuring their Perceived Value
 
How NOT to Aggregrate Polling Data
How NOT to Aggregrate Polling DataHow NOT to Aggregrate Polling Data
How NOT to Aggregrate Polling Data
 
Essential econometrics for data scientists
Essential econometrics for data scientistsEssential econometrics for data scientists
Essential econometrics for data scientists
 
Michael Habib – Lightning talk at NISO Altmetrics Initiative
Michael Habib – Lightning talk at NISO Altmetrics InitiativeMichael Habib – Lightning talk at NISO Altmetrics Initiative
Michael Habib – Lightning talk at NISO Altmetrics Initiative
 
Context-Aware Recommender Systems for Mobile Devices
Context-Aware Recommender Systems for Mobile DevicesContext-Aware Recommender Systems for Mobile Devices
Context-Aware Recommender Systems for Mobile Devices
 
Online Travel Reviews on Mobile Applications when making travel plans: Uses a...
Online Travel Reviews on Mobile Applications when making travel plans: Uses a...Online Travel Reviews on Mobile Applications when making travel plans: Uses a...
Online Travel Reviews on Mobile Applications when making travel plans: Uses a...
 
Strategic Visitor Flows (SVF) analysis using mobile data
Strategic Visitor Flows (SVF) analysis using mobile dataStrategic Visitor Flows (SVF) analysis using mobile data
Strategic Visitor Flows (SVF) analysis using mobile data
 
An online evaluation of explicit feedback mechanisms for recommender systems
An online evaluation of explicit feedback mechanisms for recommender systemsAn online evaluation of explicit feedback mechanisms for recommender systems
An online evaluation of explicit feedback mechanisms for recommender systems
 

Viewers also liked

Viewers also liked (20)

Student Preferences for Social Media Source Characteristics
Student Preferences for Social Media Source CharacteristicsStudent Preferences for Social Media Source Characteristics
Student Preferences for Social Media Source Characteristics
 
Duetto: An introduction to Revenue Judo
Duetto: An introduction to Revenue JudoDuetto: An introduction to Revenue Judo
Duetto: An introduction to Revenue Judo
 
Ontology-based Matchmaking to Provide Personalized Offers
Ontology-based Matchmaking to Provide Personalized OffersOntology-based Matchmaking to Provide Personalized Offers
Ontology-based Matchmaking to Provide Personalized Offers
 
DFRC from data to knowledge. Learn from your data. Measure, Manage, Innovate,...
DFRC from data to knowledge. Learn from your data. Measure, Manage, Innovate,...DFRC from data to knowledge. Learn from your data. Measure, Manage, Innovate,...
DFRC from data to knowledge. Learn from your data. Measure, Manage, Innovate,...
 
Social CRM capabilities and readiness: findings from Greek tourism firms
Social CRM capabilities and readiness: findings from Greek tourism firmsSocial CRM capabilities and readiness: findings from Greek tourism firms
Social CRM capabilities and readiness: findings from Greek tourism firms
 
Predicting Tourism Demand Using Big Data - Issues and Challenges
Predicting Tourism Demand Using Big Data - Issues and ChallengesPredicting Tourism Demand Using Big Data - Issues and Challenges
Predicting Tourism Demand Using Big Data - Issues and Challenges
 
Exploring the roles of hosts' attachment and psychological ownership in an Ai...
Exploring the roles of hosts' attachment and psychological ownership in an Ai...Exploring the roles of hosts' attachment and psychological ownership in an Ai...
Exploring the roles of hosts' attachment and psychological ownership in an Ai...
 
Can we predict your sentiments by listening to your peers?
Can we predict your sentiments by listening to your peers?Can we predict your sentiments by listening to your peers?
Can we predict your sentiments by listening to your peers?
 
The development of a business model for the implementation of augmented reali...
The development of a business model for the implementation of augmented reali...The development of a business model for the implementation of augmented reali...
The development of a business model for the implementation of augmented reali...
 
RC AirWorks: Drones for Tourism Destination Promotion
RC AirWorks: Drones for Tourism Destination PromotionRC AirWorks: Drones for Tourism Destination Promotion
RC AirWorks: Drones for Tourism Destination Promotion
 
Trends in travel agencies' e business perspectives of human resource sector
Trends in travel agencies' e business perspectives of human resource sectorTrends in travel agencies' e business perspectives of human resource sector
Trends in travel agencies' e business perspectives of human resource sector
 
MOOC Camp: A flipped classroom and blended learning model
MOOC Camp: A flipped classroom and blended learning modelMOOC Camp: A flipped classroom and blended learning model
MOOC Camp: A flipped classroom and blended learning model
 
The use of social media and its impacts on consumer behavior: the context of ...
The use of social media and its impacts on consumer behavior: the context of ...The use of social media and its impacts on consumer behavior: the context of ...
The use of social media and its impacts on consumer behavior: the context of ...
 
How do we search? Themes and challenges
How do we search? Themes and challengesHow do we search? Themes and challenges
How do we search? Themes and challenges
 
Tracking tourist spatial-temporal behavior in urban places, a methodological ...
Tracking tourist spatial-temporal behavior in urban places, a methodological ...Tracking tourist spatial-temporal behavior in urban places, a methodological ...
Tracking tourist spatial-temporal behavior in urban places, a methodological ...
 
Users creativity in mobile computing travel platforms
Users creativity in mobile computing travel platformsUsers creativity in mobile computing travel platforms
Users creativity in mobile computing travel platforms
 
Surving and thriving in your early academic career
Surving and thriving in your early academic careerSurving and thriving in your early academic career
Surving and thriving in your early academic career
 
An exploration of user-driven assessments of travel enhancing apps
An exploration of user-driven assessments of travel enhancing appsAn exploration of user-driven assessments of travel enhancing apps
An exploration of user-driven assessments of travel enhancing apps
 
Psychological antecedents of smartphone users behaviour along the mobile cust...
Psychological antecedents of smartphone users behaviour along the mobile cust...Psychological antecedents of smartphone users behaviour along the mobile cust...
Psychological antecedents of smartphone users behaviour along the mobile cust...
 
Factors affecting the performance of tourism crowdfunding projects an empiric...
Factors affecting the performance of tourism crowdfunding projects an empiric...Factors affecting the performance of tourism crowdfunding projects an empiric...
Factors affecting the performance of tourism crowdfunding projects an empiric...
 

Similar to Contextual information elicitation in travel recommender systems

Context-Aware Points of Interest Suggestion with Dynamic Weather Data Management
Context-Aware Points of Interest Suggestion with Dynamic Weather Data ManagementContext-Aware Points of Interest Suggestion with Dynamic Weather Data Management
Context-Aware Points of Interest Suggestion with Dynamic Weather Data ManagementMatthias Braunhofer
 
Tutorial: Context In Recommender Systems
Tutorial: Context In Recommender SystemsTutorial: Context In Recommender Systems
Tutorial: Context In Recommender SystemsYONG ZHENG
 
Recommending Sequences RecTour 2017
Recommending Sequences RecTour 2017Recommending Sequences RecTour 2017
Recommending Sequences RecTour 2017Gunjan Kumar
 
Context-aware Recommendation: A Quick View
Context-aware Recommendation: A Quick ViewContext-aware Recommendation: A Quick View
Context-aware Recommendation: A Quick ViewYONG ZHENG
 
[WI 2017] Context Suggestion: Empirical Evaluations vs User Studies
[WI 2017] Context Suggestion: Empirical Evaluations vs User Studies[WI 2017] Context Suggestion: Empirical Evaluations vs User Studies
[WI 2017] Context Suggestion: Empirical Evaluations vs User StudiesYONG ZHENG
 
Harnessing Ratings and Aspect-Sentiment to Estimate Contradiction Intensity i...
Harnessing Ratings and Aspect-Sentiment to Estimate Contradiction Intensity i...Harnessing Ratings and Aspect-Sentiment to Estimate Contradiction Intensity i...
Harnessing Ratings and Aspect-Sentiment to Estimate Contradiction Intensity i...Ismail BADACHE
 
Parsimonious and Adaptive Contextual Information Acquisition in Recommender S...
Parsimonious and Adaptive Contextual Information Acquisition in Recommender S...Parsimonious and Adaptive Contextual Information Acquisition in Recommender S...
Parsimonious and Adaptive Contextual Information Acquisition in Recommender S...Matthias Braunhofer
 
Hybridisation Techniques for Cold-Starting Context-Aware Recommender Systems
Hybridisation Techniques for Cold-Starting Context-Aware Recommender SystemsHybridisation Techniques for Cold-Starting Context-Aware Recommender Systems
Hybridisation Techniques for Cold-Starting Context-Aware Recommender SystemsMatthias Braunhofer
 
Gunjan insight student conference v2
Gunjan insight student conference v2Gunjan insight student conference v2
Gunjan insight student conference v2Gunjan Kumar
 
Continuous Evaluation of Collaborative Recommender Systems in Data Stream Man...
Continuous Evaluation of Collaborative Recommender Systems in Data Stream Man...Continuous Evaluation of Collaborative Recommender Systems in Data Stream Man...
Continuous Evaluation of Collaborative Recommender Systems in Data Stream Man...Dr. Cornelius Ludmann
 
MAC411(A) Analysis in Communication Researc.ppt
MAC411(A) Analysis in Communication Researc.pptMAC411(A) Analysis in Communication Researc.ppt
MAC411(A) Analysis in Communication Researc.pptPreciousOsoOla
 
GECCO 2014 - Learning Classifier System Tutorial
GECCO 2014 - Learning Classifier System TutorialGECCO 2014 - Learning Classifier System Tutorial
GECCO 2014 - Learning Classifier System TutorialPier Luca Lanzi
 
Replicable Evaluation of Recommender Systems
Replicable Evaluation of Recommender SystemsReplicable Evaluation of Recommender Systems
Replicable Evaluation of Recommender SystemsAlejandro Bellogin
 
Usability Assessment of a Context-Aware and Personality-Based Mobile Recommen...
Usability Assessment of a Context-Aware and Personality-Based Mobile Recommen...Usability Assessment of a Context-Aware and Personality-Based Mobile Recommen...
Usability Assessment of a Context-Aware and Personality-Based Mobile Recommen...Matthias Braunhofer
 
Impact of Recruitment & Selection Processes on Employee Performance: A Study ...
Impact of Recruitment & Selection Processes on Employee Performance: A Study ...Impact of Recruitment & Selection Processes on Employee Performance: A Study ...
Impact of Recruitment & Selection Processes on Employee Performance: A Study ...Sheheryar Alvi
 
Finding and Quantifying Temporal-Aware Contradiction in Reviews
Finding and Quantifying Temporal-Aware Contradiction in ReviewsFinding and Quantifying Temporal-Aware Contradiction in Reviews
Finding and Quantifying Temporal-Aware Contradiction in ReviewsIsmail BADACHE
 

Similar to Contextual information elicitation in travel recommender systems (20)

Context-Aware Points of Interest Suggestion with Dynamic Weather Data Management
Context-Aware Points of Interest Suggestion with Dynamic Weather Data ManagementContext-Aware Points of Interest Suggestion with Dynamic Weather Data Management
Context-Aware Points of Interest Suggestion with Dynamic Weather Data Management
 
Context-Aware Points of Interest Suggestion with Dynamic Weather Data Management
Context-Aware Points of Interest Suggestion with Dynamic Weather Data ManagementContext-Aware Points of Interest Suggestion with Dynamic Weather Data Management
Context-Aware Points of Interest Suggestion with Dynamic Weather Data Management
 
Tutorial: Context In Recommender Systems
Tutorial: Context In Recommender SystemsTutorial: Context In Recommender Systems
Tutorial: Context In Recommender Systems
 
South Tyrol Suggests - STS
South Tyrol Suggests - STSSouth Tyrol Suggests - STS
South Tyrol Suggests - STS
 
Recommending Sequences RecTour 2017
Recommending Sequences RecTour 2017Recommending Sequences RecTour 2017
Recommending Sequences RecTour 2017
 
Context-aware Recommendation: A Quick View
Context-aware Recommendation: A Quick ViewContext-aware Recommendation: A Quick View
Context-aware Recommendation: A Quick View
 
GKumarAICS
GKumarAICSGKumarAICS
GKumarAICS
 
User Personality and the New User Problem in a Context-­‐Aware POI Recommende...
User Personality and the New User Problem in a Context-­‐Aware POI Recommende...User Personality and the New User Problem in a Context-­‐Aware POI Recommende...
User Personality and the New User Problem in a Context-­‐Aware POI Recommende...
 
[WI 2017] Context Suggestion: Empirical Evaluations vs User Studies
[WI 2017] Context Suggestion: Empirical Evaluations vs User Studies[WI 2017] Context Suggestion: Empirical Evaluations vs User Studies
[WI 2017] Context Suggestion: Empirical Evaluations vs User Studies
 
Harnessing Ratings and Aspect-Sentiment to Estimate Contradiction Intensity i...
Harnessing Ratings and Aspect-Sentiment to Estimate Contradiction Intensity i...Harnessing Ratings and Aspect-Sentiment to Estimate Contradiction Intensity i...
Harnessing Ratings and Aspect-Sentiment to Estimate Contradiction Intensity i...
 
Parsimonious and Adaptive Contextual Information Acquisition in Recommender S...
Parsimonious and Adaptive Contextual Information Acquisition in Recommender S...Parsimonious and Adaptive Contextual Information Acquisition in Recommender S...
Parsimonious and Adaptive Contextual Information Acquisition in Recommender S...
 
Hybridisation Techniques for Cold-Starting Context-Aware Recommender Systems
Hybridisation Techniques for Cold-Starting Context-Aware Recommender SystemsHybridisation Techniques for Cold-Starting Context-Aware Recommender Systems
Hybridisation Techniques for Cold-Starting Context-Aware Recommender Systems
 
Gunjan insight student conference v2
Gunjan insight student conference v2Gunjan insight student conference v2
Gunjan insight student conference v2
 
Continuous Evaluation of Collaborative Recommender Systems in Data Stream Man...
Continuous Evaluation of Collaborative Recommender Systems in Data Stream Man...Continuous Evaluation of Collaborative Recommender Systems in Data Stream Man...
Continuous Evaluation of Collaborative Recommender Systems in Data Stream Man...
 
MAC411(A) Analysis in Communication Researc.ppt
MAC411(A) Analysis in Communication Researc.pptMAC411(A) Analysis in Communication Researc.ppt
MAC411(A) Analysis in Communication Researc.ppt
 
GECCO 2014 - Learning Classifier System Tutorial
GECCO 2014 - Learning Classifier System TutorialGECCO 2014 - Learning Classifier System Tutorial
GECCO 2014 - Learning Classifier System Tutorial
 
Replicable Evaluation of Recommender Systems
Replicable Evaluation of Recommender SystemsReplicable Evaluation of Recommender Systems
Replicable Evaluation of Recommender Systems
 
Usability Assessment of a Context-Aware and Personality-Based Mobile Recommen...
Usability Assessment of a Context-Aware and Personality-Based Mobile Recommen...Usability Assessment of a Context-Aware and Personality-Based Mobile Recommen...
Usability Assessment of a Context-Aware and Personality-Based Mobile Recommen...
 
Impact of Recruitment & Selection Processes on Employee Performance: A Study ...
Impact of Recruitment & Selection Processes on Employee Performance: A Study ...Impact of Recruitment & Selection Processes on Employee Performance: A Study ...
Impact of Recruitment & Selection Processes on Employee Performance: A Study ...
 
Finding and Quantifying Temporal-Aware Contradiction in Reviews
Finding and Quantifying Temporal-Aware Contradiction in ReviewsFinding and Quantifying Temporal-Aware Contradiction in Reviews
Finding and Quantifying Temporal-Aware Contradiction in Reviews
 

Recently uploaded

VIP Call Girls in Noida 9711199012 Escorts in Greater Noida,Ms
VIP Call Girls in Noida 9711199012 Escorts in Greater Noida,MsVIP Call Girls in Noida 9711199012 Escorts in Greater Noida,Ms
VIP Call Girls in Noida 9711199012 Escorts in Greater Noida,Msankitnayak356677
 
Italia Lucca 1 Un tesoro nascosto tra le sue mura
Italia Lucca 1 Un tesoro nascosto tra le sue muraItalia Lucca 1 Un tesoro nascosto tra le sue mura
Italia Lucca 1 Un tesoro nascosto tra le sue murasandamichaela *
 
Top 10 Traditional Indian Handicrafts.pptx
Top 10 Traditional Indian Handicrafts.pptxTop 10 Traditional Indian Handicrafts.pptx
Top 10 Traditional Indian Handicrafts.pptxdishha99
 
"Fly with Ease: Booking Your Flights with Air Europa"
"Fly with Ease: Booking Your Flights with Air Europa""Fly with Ease: Booking Your Flights with Air Europa"
"Fly with Ease: Booking Your Flights with Air Europa"flyn goo
 
Moving to Italy - A Relocation Rollercoaster
Moving to Italy - A Relocation RollercoasterMoving to Italy - A Relocation Rollercoaster
Moving to Italy - A Relocation RollercoasterStefSmulders1
 
Exploring Sicily Your Comprehensive Ebook Travel Guide
Exploring Sicily Your Comprehensive Ebook Travel GuideExploring Sicily Your Comprehensive Ebook Travel Guide
Exploring Sicily Your Comprehensive Ebook Travel GuideTime for Sicily
 
Akshay Mehndiratta Summer Special Light Meal Ideas From Across India.pptx
Akshay Mehndiratta Summer Special Light Meal Ideas From Across India.pptxAkshay Mehndiratta Summer Special Light Meal Ideas From Across India.pptx
Akshay Mehndiratta Summer Special Light Meal Ideas From Across India.pptxAkshay Mehndiratta
 
(8264348440) 🔝 Call Girls In Nand Nagri 🔝 Delhi NCR
(8264348440) 🔝 Call Girls In Nand Nagri 🔝 Delhi NCR(8264348440) 🔝 Call Girls In Nand Nagri 🔝 Delhi NCR
(8264348440) 🔝 Call Girls In Nand Nagri 🔝 Delhi NCRsoniya singh
 
How can I fly with the British Airways Unaccompanied Minor Policy?
How can I fly with the British Airways Unaccompanied Minor Policy?How can I fly with the British Airways Unaccompanied Minor Policy?
How can I fly with the British Airways Unaccompanied Minor Policy?flightsvillacom
 
DARK TRAVEL AGENCY presented by Khuda Bux
DARK TRAVEL AGENCY presented by Khuda BuxDARK TRAVEL AGENCY presented by Khuda Bux
DARK TRAVEL AGENCY presented by Khuda BuxBeEducate
 
08448380779 Call Girls In Shahdara Women Seeking Men
08448380779 Call Girls In Shahdara Women Seeking Men08448380779 Call Girls In Shahdara Women Seeking Men
08448380779 Call Girls In Shahdara Women Seeking MenDelhi Call girls
 
08448380779 Call Girls In Chhattarpur Women Seeking Men
08448380779 Call Girls In Chhattarpur Women Seeking Men08448380779 Call Girls In Chhattarpur Women Seeking Men
08448380779 Call Girls In Chhattarpur Women Seeking MenDelhi Call girls
 
Hoi An Ancient Town, Vietnam (越南 會安古鎮).ppsx
Hoi An Ancient Town, Vietnam (越南 會安古鎮).ppsxHoi An Ancient Town, Vietnam (越南 會安古鎮).ppsx
Hoi An Ancient Town, Vietnam (越南 會安古鎮).ppsxChung Yen Chang
 
BERMUDA Triangle the mystery of life.pptx
BERMUDA Triangle the mystery of life.pptxBERMUDA Triangle the mystery of life.pptx
BERMUDA Triangle the mystery of life.pptxseribangash
 
best weekend places near delhi where you should visit.pdf
best weekend places near delhi where you should visit.pdfbest weekend places near delhi where you should visit.pdf
best weekend places near delhi where you should visit.pdftour guide
 
Night 7k Call Girls Noida Sector 93 Escorts Call Me: 8448380779
Night 7k Call Girls Noida Sector 93 Escorts Call Me: 8448380779Night 7k Call Girls Noida Sector 93 Escorts Call Me: 8448380779
Night 7k Call Girls Noida Sector 93 Escorts Call Me: 8448380779Delhi Call girls
 

Recently uploaded (20)

VIP Call Girls in Noida 9711199012 Escorts in Greater Noida,Ms
VIP Call Girls in Noida 9711199012 Escorts in Greater Noida,MsVIP Call Girls in Noida 9711199012 Escorts in Greater Noida,Ms
VIP Call Girls in Noida 9711199012 Escorts in Greater Noida,Ms
 
Italia Lucca 1 Un tesoro nascosto tra le sue mura
Italia Lucca 1 Un tesoro nascosto tra le sue muraItalia Lucca 1 Un tesoro nascosto tra le sue mura
Italia Lucca 1 Un tesoro nascosto tra le sue mura
 
Top 10 Traditional Indian Handicrafts.pptx
Top 10 Traditional Indian Handicrafts.pptxTop 10 Traditional Indian Handicrafts.pptx
Top 10 Traditional Indian Handicrafts.pptx
 
"Fly with Ease: Booking Your Flights with Air Europa"
"Fly with Ease: Booking Your Flights with Air Europa""Fly with Ease: Booking Your Flights with Air Europa"
"Fly with Ease: Booking Your Flights with Air Europa"
 
Moving to Italy - A Relocation Rollercoaster
Moving to Italy - A Relocation RollercoasterMoving to Italy - A Relocation Rollercoaster
Moving to Italy - A Relocation Rollercoaster
 
Exploring Sicily Your Comprehensive Ebook Travel Guide
Exploring Sicily Your Comprehensive Ebook Travel GuideExploring Sicily Your Comprehensive Ebook Travel Guide
Exploring Sicily Your Comprehensive Ebook Travel Guide
 
Call Girls In Munirka 📱 9999965857 🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SERVICE
Call Girls In Munirka 📱  9999965857  🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SERVICECall Girls In Munirka 📱  9999965857  🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SERVICE
Call Girls In Munirka 📱 9999965857 🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SERVICE
 
Call Girls 🫤 Connaught Place ➡️ 9999965857 ➡️ Delhi 🫦 Russian Escorts FULL ...
Call Girls 🫤 Connaught Place ➡️ 9999965857  ➡️ Delhi 🫦  Russian Escorts FULL ...Call Girls 🫤 Connaught Place ➡️ 9999965857  ➡️ Delhi 🫦  Russian Escorts FULL ...
Call Girls 🫤 Connaught Place ➡️ 9999965857 ➡️ Delhi 🫦 Russian Escorts FULL ...
 
Akshay Mehndiratta Summer Special Light Meal Ideas From Across India.pptx
Akshay Mehndiratta Summer Special Light Meal Ideas From Across India.pptxAkshay Mehndiratta Summer Special Light Meal Ideas From Across India.pptx
Akshay Mehndiratta Summer Special Light Meal Ideas From Across India.pptx
 
Rohini Sector 18 Call Girls Delhi 9999965857 @Sabina Saikh No Advance
Rohini Sector 18 Call Girls Delhi 9999965857 @Sabina Saikh No AdvanceRohini Sector 18 Call Girls Delhi 9999965857 @Sabina Saikh No Advance
Rohini Sector 18 Call Girls Delhi 9999965857 @Sabina Saikh No Advance
 
(8264348440) 🔝 Call Girls In Nand Nagri 🔝 Delhi NCR
(8264348440) 🔝 Call Girls In Nand Nagri 🔝 Delhi NCR(8264348440) 🔝 Call Girls In Nand Nagri 🔝 Delhi NCR
(8264348440) 🔝 Call Girls In Nand Nagri 🔝 Delhi NCR
 
Call Girls Service !! New Friends Colony!! @9999965857 Delhi 🫦 No Advance VV...
Call Girls Service !! New Friends Colony!! @9999965857 Delhi 🫦 No Advance  VV...Call Girls Service !! New Friends Colony!! @9999965857 Delhi 🫦 No Advance  VV...
Call Girls Service !! New Friends Colony!! @9999965857 Delhi 🫦 No Advance VV...
 
How can I fly with the British Airways Unaccompanied Minor Policy?
How can I fly with the British Airways Unaccompanied Minor Policy?How can I fly with the British Airways Unaccompanied Minor Policy?
How can I fly with the British Airways Unaccompanied Minor Policy?
 
DARK TRAVEL AGENCY presented by Khuda Bux
DARK TRAVEL AGENCY presented by Khuda BuxDARK TRAVEL AGENCY presented by Khuda Bux
DARK TRAVEL AGENCY presented by Khuda Bux
 
08448380779 Call Girls In Shahdara Women Seeking Men
08448380779 Call Girls In Shahdara Women Seeking Men08448380779 Call Girls In Shahdara Women Seeking Men
08448380779 Call Girls In Shahdara Women Seeking Men
 
08448380779 Call Girls In Chhattarpur Women Seeking Men
08448380779 Call Girls In Chhattarpur Women Seeking Men08448380779 Call Girls In Chhattarpur Women Seeking Men
08448380779 Call Girls In Chhattarpur Women Seeking Men
 
Hoi An Ancient Town, Vietnam (越南 會安古鎮).ppsx
Hoi An Ancient Town, Vietnam (越南 會安古鎮).ppsxHoi An Ancient Town, Vietnam (越南 會安古鎮).ppsx
Hoi An Ancient Town, Vietnam (越南 會安古鎮).ppsx
 
BERMUDA Triangle the mystery of life.pptx
BERMUDA Triangle the mystery of life.pptxBERMUDA Triangle the mystery of life.pptx
BERMUDA Triangle the mystery of life.pptx
 
best weekend places near delhi where you should visit.pdf
best weekend places near delhi where you should visit.pdfbest weekend places near delhi where you should visit.pdf
best weekend places near delhi where you should visit.pdf
 
Night 7k Call Girls Noida Sector 93 Escorts Call Me: 8448380779
Night 7k Call Girls Noida Sector 93 Escorts Call Me: 8448380779Night 7k Call Girls Noida Sector 93 Escorts Call Me: 8448380779
Night 7k Call Girls Noida Sector 93 Escorts Call Me: 8448380779
 

Contextual information elicitation in travel recommender systems

  • 1. ENTER 2016 Research Track Slide Number 1 Contextual Information Elicitation in Travel Recommender Systems Matthias Braunhofer and Francesco Ricci Free University of Bozen - Bolzano, Italy {mbraunhofer,fricci}@unibz.it http://www.inf.unibz.it
  • 2. ENTER 2016 Research Track Slide Number 2 Agenda • Introduction • Related Work • Selective Context Acquisition • Experimental Evaluation and Results • Conclusions
  • 3. ENTER 2016 Research Track Slide Number 4 Context-Aware Recommender Systems (CARSs) • CARSs provide better recommendations by incorporating contextual information (e.g., time and weather) into the recommendation process STS (South Tyrol Suggests)
  • 4. ENTER 2016 Research Track Slide Number 5 Context Acquisition Problem of CARSs • How to identify and acquire the truly relevant contextual factors that influence the user preferences and decision making process?
  • 5. ENTER 2016 Research Track Slide Number 6 STS w/o Selective Context Acquisition We can’t elicit the conditions for all the available contextual factors when the user rates a POI.
  • 6. ENTER 2016 Research Track Slide Number 7 STS w/ Selective Context Acquisition Rather, we must elicit the conditions of a small subset of most important contextual factors.
  • 7. ENTER 2016 Research Track Slide Number 8 Agenda
  • 8. ENTER 2016 Research Track Slide Number 9 Context Acquisition Problem in Commercial Systems • Numerous commercial systems in the tourism domain face the context acquisition problem TripAdvisor Foursquare
  • 9. ENTER 2016 Research Track Slide Number 10 A Priori Context Selection • Web survey in which users evaluate the influence of contextual conditions on POI categories • Allows to identify the relevant factors before collecting ratings (Baltrunas et al., 2012)
  • 10. ENTER 2016 Research Track Slide Number 11 A Posteriori Context Selection • Several statistic-based methods for detecting the relevant context after collecting ratings • Results show a significant difference in prediction of ratings in relevant vs. irrelevant context (Odić et al., 2013)
  • 11. ENTER 2016 Research Track Slide Number 12 Agenda
  • 12. ENTER 2016 Research Track Slide Number 13 Parsimonious and Adaptive Context Acquisition • Main idea: for each user-item pair (u, i), identify the contextual factors that when acquired with u’s rating for i improve most the long term performance of the recommender – Heuristic: acquire the contextual factors that have the largest impact on rating prediction • Challenge: how to quantify these impacts?
  • 13. ENTER 2016 Research Track Slide Number 14 CARS Prediction Model • We use a new variant of Context-Aware Matrix Factorization (CAMF) (Baltrunas et al., 2011) that treats contextual conditions similarly to either item or user attributes ˆruic1,...,ck = (qi + xa )T (pu + yb )+ ri b∈A(u)∪C(u) ∑ + bu a∈A(i)∪C(i) ∑ Latent vector of item i Latent vector of user u Latent vectors of conventional (e.g., genre) and contextual item attributes (e.g., weather) Avg. rating for item i Bias of user uLatent vectors of conventional (e.g., age) and contextual user attributes (e.g., mood)
  • 14. ENTER 2016 Research Track Slide Number 15 Largest Deviation • Given (u, i), it computes a relevance score for each contextual factor Cj by first measuring the “impact” of each contextual condition cj C∈ j: • Finally, it computes for each factor the average of these deviation scores, and selects the contextual factors with the largest average scores ˆwuicj = fcj ˆruicj − ˆrui Normalized freq. of cj Rating prediction when cj holds Predicted context-free rating
  • 15. ENTER 2016 Research Track Slide Number 16 Illustrative Example • Let ȓAliceSkiingSunny = 5, ȓAliceSkiing = 3.5 & fSunny = 0.2. Then, the impact of the “Sunny” condition is: – ŵAliceSkiingSunny = 0.2 · |5 - 3.5| = 0.3 • Let ŵAliceSkiingCloudy= 0.2, ŵAliceSkiingRainy= 0.3 & ŵAliceSkiingSnowy= 0.1, the impacts of the other weather conditions. Then, the overall impact of the “Weather” factor is: – (0.3 + 0.2 + 0.3 + 0.1) ÷ 5 = 0.18
  • 16. ENTER 2016 Research Track Slide Number 17 Agenda
  • 17. ENTER 2016 Research Track Slide Number 18 Datasets Dataset STS TripAdvisor Rating scale 1-5 1-5 Ratings 2,534 4,147 Users 325 3,916 Items 249 569 Contextual factors 14 3 Contextual conditions 57 31 Avg. # of factors known for each rating 1.49 3 User attributes 7 2 Item attributes 1 12 In STS when a user rates a POI she commonly specifies at most 4 out of the 14 factors! In STS when a user rates a POI she commonly specifies at most 4 out of the 14 factors!
  • 18. ENTER 2016 Research Track Slide Number 19 Evaluation Procedure: Overview • Repeated random sampling (20 times): – Randomly partition the ratings into 3 subsets – For each user-item pair (u, i) in the candidate set, compute the N most relevant contextual factors and transfer the corresponding rating and context information ruic in the candidate set to the training set as ruic’ with c’ c containing the conditions for these factors, if any⊆ – Measure prediction accuracy (MAE) and ranking quality (Precision) on testing set, after training the prediction model on extended training set – Repeat Training set (25%) Candidate set (50%) Testing set (25%)
  • 19. ENTER 2016 Research Track Slide Number 20 user-item pair Evaluation Procedure: Example (Alice, Skiing) Season and Weather rAlice Skiing Winter, Sunny, Warm, Morning = 5 rAlice Skiing Winter, Sunny = 5 top two contextual factors rating in candidate set rating transferred to training set + + =
  • 20. ENTER 2016 Research Track Slide Number 21 Baseline Methods for Evaluation • Mutual Information: given a user-item pair (u,i), computes the relevance for a contextual factor Cj as the mutual information between ratings for items belonging to i’s category (Baltrunas et al., 2012) • Freeman-Halton Test: calculates the relevance of Cj using the Freeman-Halton test (Odić et al., 2013) • mRMR: ranks each Cj according to its relevance to the rating variable and redundancy to other contextual factors (Peng et al., 2005)
  • 21. ENTER 2016 Research Track Slide Number 22 Evaluation Results: Prediction Accuracy
  • 22. ENTER 2016 Research Track Slide Number 23 Evaluation Results: Ranking Quality
  • 23. ENTER 2016 Research Track Slide Number 24 Evaluation Results: # of Acquired Conditions
  • 24. ENTER 2016 Research Track Slide Number 25 Agenda
  • 25. ENTER 2016 Research Track Slide Number 26 Conclusions • Using Largest Deviation, we know that we can ask only the contextual factors C1, C2 and C3 when we ask user u to rate item i
  • 26. ENTER 2016 Research Track Slide Number 29 Questions? Thank you.