SlideShare a Scribd company logo
1 of 17
Trust-Based Rating Prediction for Recommendation in Web 2.0 Collaborative Learning Social Software ITHET  29th April – 1st May 2010, Cappadocia, Turkey Na Li, Sandy El Helou, Denis Gillet Real-Time Coordination and Distributed Interaction Systems (ReAct)  Automatic Control Lab, Swiss Federal Institute of Technology in Lausanne
Outline Introduction Collaborative Learning Domain 3A Interaction Model Trust-Based Rating Prediction Approach Evaluation and Results Conclusion and Future Work
Introduction Web 2.0 social software A large amount of user generated content New challenge: selection of useful resources RSS Feeds Pictures Pictures Wiki Pages Documents Videos
Introduction Rating systems Evaluate quality of content in open environment Provide recommendation for different users
Introduction Rating systems – application level Rating systems – academic research level TidalTrust (J. Golbeck), MoleTrust(P. Massa) User explicitly specifies a trust value towards another user Build trust network, Random walk in trust network Personalized rating prediction
Collaborative Learning Domain Collaborative learning environment Unlike e-commerce and review sites Gift economy ,[object Object],Evaluate user generated content Filter helpful learning resources, peers and group activities Personalized rating prediction for recommendation
3A Interaction Model
Trust-Based Rating Prediction Approach Objective Build users’ trust network using 3A graph structure Personalize the rating prediction Infer trust value in an implicit way ,[object Object],What influences rating opinion: similarity and familiarity People tend to trust the opinions of acquaintance and those having similar interests and tastes.
Trust-Based Rating Prediction Approach Trust measurement Multi-relational trust metric Build a “Web of Trust” for a particular user using heterogeneous types of relationships ,[object Object],Direct trust Indirect trust Trust How Much?
Trust-Based Rating Prediction Approach Direct trust (DT): derived from a particular type of relationship W (Membership): weight of “membership” relationship N (Alice, Membership): number of group activities Alice joins Is Member of Advanced Algorithms Group Activity Alice
Trust-Based Rating Prediction Approach Trust propagation Propagation distance (PD) Bob Commented by Article Rated by Sara Create Is Member Has Member French Learning Activity Luis Alice Rate Video Rated by Ben Created by Jack Propagate Propagate Propagate PD
Trust-Based Rating Prediction Approach Indirect Trust (IT) Inference
Trust-Based Rating Prediction Approach Rating prediction from a user to an item Using user’s “Web of Trust” People in “Web of Trust” are seen as trustable Average of all the rating scores given by trustable people, weighted by their trust value
Evaluation and Results Using Remashed data set 50 users, 6000 items, 3000 tags and 450 ratings “Leave-one-out” method Compare “predicted score – actual score” deviation of trust-based prediction and simple average
Evaluation and Results Change parameters Weights for relationships doesn’t make a significant difference in rating prediction Increasing size of trust network might add noise, lead to bigger prediction error
Conclusion and Future Work Propose a trust-based rating prediction approach, inferring trust in an implicit way Provide personalized rating prediction so as to evaluate user-generated content in collaborative learning environment Future deploy and evaluation will be conducted in a collaborative learning platform, namely Graaasp(graaasp.epfl.ch)
Questions?

More Related Content

What's hot

Rep on the Roll A peer to peer reputation system based on a rolling blockchain
Rep on the Roll A peer to peer reputation system based on a rolling blockchainRep on the Roll A peer to peer reputation system based on a rolling blockchain
Rep on the Roll A peer to peer reputation system based on a rolling blockchainRichard Dennis
 
How to conduct a social network analysis: A tool for empowering teams and wor...
How to conduct a social network analysis: A tool for empowering teams and wor...How to conduct a social network analysis: A tool for empowering teams and wor...
How to conduct a social network analysis: A tool for empowering teams and wor...Jeromy Anglim
 
Link Prediction Survey
Link Prediction SurveyLink Prediction Survey
Link Prediction SurveyPatrick Walter
 
Beyond text qa multimedia answer generation by harvesting web information
Beyond text qa multimedia answer generation by harvesting web informationBeyond text qa multimedia answer generation by harvesting web information
Beyond text qa multimedia answer generation by harvesting web informationJPINFOTECH JAYAPRAKASH
 
Hybrid sentiment and network analysis of social opinion polarization icoict
Hybrid sentiment and network analysis of social opinion polarization   icoictHybrid sentiment and network analysis of social opinion polarization   icoict
Hybrid sentiment and network analysis of social opinion polarization icoictAndry Alamsyah
 
DYNAMIC LARGE SCALE DATA ON TWITTER USING SENTIMENT ANALYSIS AND TOPIC MODELING
DYNAMIC LARGE SCALE DATA ON TWITTER USING SENTIMENT ANALYSIS AND TOPIC MODELINGDYNAMIC LARGE SCALE DATA ON TWITTER USING SENTIMENT ANALYSIS AND TOPIC MODELING
DYNAMIC LARGE SCALE DATA ON TWITTER USING SENTIMENT ANALYSIS AND TOPIC MODELINGAndry Alamsyah
 
Social Network Analysis
Social Network AnalysisSocial Network Analysis
Social Network AnalysisSujoy Bag
 
Dissemination of Awareness Evolution “What is really going on?” Pilkada 2015 ...
Dissemination of Awareness Evolution “What is really going on?” Pilkada 2015 ...Dissemination of Awareness Evolution “What is really going on?” Pilkada 2015 ...
Dissemination of Awareness Evolution “What is really going on?” Pilkada 2015 ...Andry Alamsyah
 
Summary on the Conference of WISE 2013
Summary on the Conference of WISE 2013Summary on the Conference of WISE 2013
Summary on the Conference of WISE 2013Yueshen Xu
 
Recommender system and big data (design a smartphone recommender system based...
Recommender system and big data (design a smartphone recommender system based...Recommender system and big data (design a smartphone recommender system based...
Recommender system and big data (design a smartphone recommender system based...Siwar Abidi
 
ACM ICTIR 2019 Slides - Santa Clara, USA
ACM ICTIR 2019 Slides -  Santa Clara, USAACM ICTIR 2019 Slides -  Santa Clara, USA
ACM ICTIR 2019 Slides - Santa Clara, USAIadh Ounis
 
Studying user footprints in different online social networks
Studying user footprints in different online social networksStudying user footprints in different online social networks
Studying user footprints in different online social networksIIIT Hyderabad
 
Designing for Collaboration: Challenges & Considerations of Multi-Use Informa...
Designing for Collaboration: Challenges & Considerations of Multi-Use Informa...Designing for Collaboration: Challenges & Considerations of Multi-Use Informa...
Designing for Collaboration: Challenges & Considerations of Multi-Use Informa...Stephanie Steinhardt
 
DEEP LEARNING SENTIMENT ANALYSIS OF AMAZON.COM REVIEWS AND RATINGS
DEEP LEARNING SENTIMENT ANALYSIS OF AMAZON.COM REVIEWS AND RATINGSDEEP LEARNING SENTIMENT ANALYSIS OF AMAZON.COM REVIEWS AND RATINGS
DEEP LEARNING SENTIMENT ANALYSIS OF AMAZON.COM REVIEWS AND RATINGSijscai
 

What's hot (20)

Rep on the Roll A peer to peer reputation system based on a rolling blockchain
Rep on the Roll A peer to peer reputation system based on a rolling blockchainRep on the Roll A peer to peer reputation system based on a rolling blockchain
Rep on the Roll A peer to peer reputation system based on a rolling blockchain
 
How to conduct a social network analysis: A tool for empowering teams and wor...
How to conduct a social network analysis: A tool for empowering teams and wor...How to conduct a social network analysis: A tool for empowering teams and wor...
How to conduct a social network analysis: A tool for empowering teams and wor...
 
At4102337341
At4102337341At4102337341
At4102337341
 
Link Prediction Survey
Link Prediction SurveyLink Prediction Survey
Link Prediction Survey
 
Beyond text qa multimedia answer generation by harvesting web information
Beyond text qa multimedia answer generation by harvesting web informationBeyond text qa multimedia answer generation by harvesting web information
Beyond text qa multimedia answer generation by harvesting web information
 
Hybrid sentiment and network analysis of social opinion polarization icoict
Hybrid sentiment and network analysis of social opinion polarization   icoictHybrid sentiment and network analysis of social opinion polarization   icoict
Hybrid sentiment and network analysis of social opinion polarization icoict
 
Recommender Systems
Recommender SystemsRecommender Systems
Recommender Systems
 
DYNAMIC LARGE SCALE DATA ON TWITTER USING SENTIMENT ANALYSIS AND TOPIC MODELING
DYNAMIC LARGE SCALE DATA ON TWITTER USING SENTIMENT ANALYSIS AND TOPIC MODELINGDYNAMIC LARGE SCALE DATA ON TWITTER USING SENTIMENT ANALYSIS AND TOPIC MODELING
DYNAMIC LARGE SCALE DATA ON TWITTER USING SENTIMENT ANALYSIS AND TOPIC MODELING
 
A trust aggregation portal
A trust aggregation portalA trust aggregation portal
A trust aggregation portal
 
Social Network Analysis
Social Network AnalysisSocial Network Analysis
Social Network Analysis
 
Dissemination of Awareness Evolution “What is really going on?” Pilkada 2015 ...
Dissemination of Awareness Evolution “What is really going on?” Pilkada 2015 ...Dissemination of Awareness Evolution “What is really going on?” Pilkada 2015 ...
Dissemination of Awareness Evolution “What is really going on?” Pilkada 2015 ...
 
Summary on the Conference of WISE 2013
Summary on the Conference of WISE 2013Summary on the Conference of WISE 2013
Summary on the Conference of WISE 2013
 
Social network analysis
Social network analysisSocial network analysis
Social network analysis
 
Recommender system and big data (design a smartphone recommender system based...
Recommender system and big data (design a smartphone recommender system based...Recommender system and big data (design a smartphone recommender system based...
Recommender system and big data (design a smartphone recommender system based...
 
Ppt
PptPpt
Ppt
 
ACM ICTIR 2019 Slides - Santa Clara, USA
ACM ICTIR 2019 Slides -  Santa Clara, USAACM ICTIR 2019 Slides -  Santa Clara, USA
ACM ICTIR 2019 Slides - Santa Clara, USA
 
Studying user footprints in different online social networks
Studying user footprints in different online social networksStudying user footprints in different online social networks
Studying user footprints in different online social networks
 
Designing for Collaboration: Challenges & Considerations of Multi-Use Informa...
Designing for Collaboration: Challenges & Considerations of Multi-Use Informa...Designing for Collaboration: Challenges & Considerations of Multi-Use Informa...
Designing for Collaboration: Challenges & Considerations of Multi-Use Informa...
 
DEEP LEARNING SENTIMENT ANALYSIS OF AMAZON.COM REVIEWS AND RATINGS
DEEP LEARNING SENTIMENT ANALYSIS OF AMAZON.COM REVIEWS AND RATINGSDEEP LEARNING SENTIMENT ANALYSIS OF AMAZON.COM REVIEWS AND RATINGS
DEEP LEARNING SENTIMENT ANALYSIS OF AMAZON.COM REVIEWS AND RATINGS
 
WISE2019 presentation
WISE2019 presentationWISE2019 presentation
WISE2019 presentation
 

Viewers also liked

Trust Modeling and Evaluation in Web 2.0 Collaborative Learning Social Softwa...
Trust Modeling and Evaluation in Web 2.0 Collaborative Learning Social Softwa...Trust Modeling and Evaluation in Web 2.0 Collaborative Learning Social Softwa...
Trust Modeling and Evaluation in Web 2.0 Collaborative Learning Social Softwa...jianjinshu
 
Stress powerpoint
Stress powerpointStress powerpoint
Stress powerpointkadams104
 
Office shark virtual private desktop guide1
Office shark virtual private desktop guide1Office shark virtual private desktop guide1
Office shark virtual private desktop guide1LeadstoneGroup
 
Brochure be doc rev.1
Brochure be doc rev.1Brochure be doc rev.1
Brochure be doc rev.1Gaetano Bruno
 
Using Social Software for Teamwork and Collaborative Project Management in Hi...
Using Social Software for Teamwork and Collaborative Project Management in Hi...Using Social Software for Teamwork and Collaborative Project Management in Hi...
Using Social Software for Teamwork and Collaborative Project Management in Hi...jianjinshu
 
Trust and Privacy in Social Learning Environments_Na Li
Trust and Privacy in Social Learning Environments_Na LiTrust and Privacy in Social Learning Environments_Na Li
Trust and Privacy in Social Learning Environments_Na Lijianjinshu
 
20100823.1215.presentation
20100823.1215.presentation20100823.1215.presentation
20100823.1215.presentationjianjinshu
 
Jtel 2010 na li
Jtel 2010 na liJtel 2010 na li
Jtel 2010 na lijianjinshu
 
Stress powerpoint
Stress powerpointStress powerpoint
Stress powerpointkadams104
 
Trust-Based Rating Prediction for Recommendation in Web 2.0 Collaborative Lea...
Trust-Based Rating Prediction for Recommendation in Web 2.0 Collaborative Lea...Trust-Based Rating Prediction for Recommendation in Web 2.0 Collaborative Lea...
Trust-Based Rating Prediction for Recommendation in Web 2.0 Collaborative Lea...jianjinshu
 

Viewers also liked (17)

Trust Modeling and Evaluation in Web 2.0 Collaborative Learning Social Softwa...
Trust Modeling and Evaluation in Web 2.0 Collaborative Learning Social Softwa...Trust Modeling and Evaluation in Web 2.0 Collaborative Learning Social Softwa...
Trust Modeling and Evaluation in Web 2.0 Collaborative Learning Social Softwa...
 
Stress powerpoint
Stress powerpointStress powerpoint
Stress powerpoint
 
Office shark virtual private desktop guide1
Office shark virtual private desktop guide1Office shark virtual private desktop guide1
Office shark virtual private desktop guide1
 
Icwl2010 epfl
Icwl2010 epflIcwl2010 epfl
Icwl2010 epfl
 
Brochure be doc rev.1
Brochure be doc rev.1Brochure be doc rev.1
Brochure be doc rev.1
 
Using Social Software for Teamwork and Collaborative Project Management in Hi...
Using Social Software for Teamwork and Collaborative Project Management in Hi...Using Social Software for Teamwork and Collaborative Project Management in Hi...
Using Social Software for Teamwork and Collaborative Project Management in Hi...
 
Trust and Privacy in Social Learning Environments_Na Li
Trust and Privacy in Social Learning Environments_Na LiTrust and Privacy in Social Learning Environments_Na Li
Trust and Privacy in Social Learning Environments_Na Li
 
20100823.1215.presentation
20100823.1215.presentation20100823.1215.presentation
20100823.1215.presentation
 
Jtel 2010 na li
Jtel 2010 na liJtel 2010 na li
Jtel 2010 na li
 
Stress powerpoint
Stress powerpointStress powerpoint
Stress powerpoint
 
Trust-Based Rating Prediction for Recommendation in Web 2.0 Collaborative Lea...
Trust-Based Rating Prediction for Recommendation in Web 2.0 Collaborative Lea...Trust-Based Rating Prediction for Recommendation in Web 2.0 Collaborative Lea...
Trust-Based Rating Prediction for Recommendation in Web 2.0 Collaborative Lea...
 
Bab 3
Bab 3Bab 3
Bab 3
 
P2
P2P2
P2
 
Presentation1
Presentation1Presentation1
Presentation1
 
Bab 6
Bab 6 Bab 6
Bab 6
 
Comp2
Comp2Comp2
Comp2
 
Comp2
Comp2Comp2
Comp2
 

Similar to Ithet

Fine-Grained Trust Assertions for Privacy Management in the Social Semantic Web
Fine-Grained Trust Assertions for Privacy Management in the Social Semantic WebFine-Grained Trust Assertions for Privacy Management in the Social Semantic Web
Fine-Grained Trust Assertions for Privacy Management in the Social Semantic WebOwen Sacco
 
Social Recommender Systems Tutorial - WWW 2011
Social Recommender Systems Tutorial - WWW 2011Social Recommender Systems Tutorial - WWW 2011
Social Recommender Systems Tutorial - WWW 2011idoguy
 
Social Network Analysis (SNA) and its implications for knowledge discovery in...
Social Network Analysis (SNA) and its implications for knowledge discovery in...Social Network Analysis (SNA) and its implications for knowledge discovery in...
Social Network Analysis (SNA) and its implications for knowledge discovery in...ACMBangalore
 
Presentation for Doctoral Consortium at UMAP'11
Presentation for Doctoral Consortium at UMAP'11Presentation for Doctoral Consortium at UMAP'11
Presentation for Doctoral Consortium at UMAP'11Thieme Hennis
 
An Unsupervised Approach For Reputation Generation
An Unsupervised Approach For Reputation GenerationAn Unsupervised Approach For Reputation Generation
An Unsupervised Approach For Reputation GenerationKayla Jones
 
Building Communities of “Trust”
 Building Communities of “Trust” Building Communities of “Trust”
Building Communities of “Trust”Micah Altman
 
“I Like” - Analysing Interactions within Social Networks to Assert the Trustw...
“I Like” - Analysing Interactions within Social Networks to Assert the Trustw...“I Like” - Analysing Interactions within Social Networks to Assert the Trustw...
“I Like” - Analysing Interactions within Social Networks to Assert the Trustw...John Breslin
 
Trust blueprints icds 2014
Trust blueprints icds 2014Trust blueprints icds 2014
Trust blueprints icds 2014George Vanecek
 
Personalizing the web building effective recommender systems
Personalizing the web building effective recommender systemsPersonalizing the web building effective recommender systems
Personalizing the web building effective recommender systemsAravindharamanan S
 
Brightspace Analytics, Insights, and Data
Brightspace Analytics, Insights, and DataBrightspace Analytics, Insights, and Data
Brightspace Analytics, Insights, and DataD2L Barry
 
iSpot Analysed: Participatory Learning and Reputation
iSpot Analysed: Participatory Learning and ReputationiSpot Analysed: Participatory Learning and Reputation
iSpot Analysed: Participatory Learning and ReputationDoug Clow
 
IRJET- Web User Trust Relationship Prediction based on Evidence Theory
IRJET- Web User Trust Relationship Prediction based on Evidence TheoryIRJET- Web User Trust Relationship Prediction based on Evidence Theory
IRJET- Web User Trust Relationship Prediction based on Evidence TheoryIRJET Journal
 
AIST 2015 Conference Paper Presentation
AIST 2015 Conference Paper PresentationAIST 2015 Conference Paper Presentation
AIST 2015 Conference Paper PresentationFalguni Roy
 
Invited talk at Future Networked Technologies / FIT-IT research calls opening...
Invited talk at Future Networked Technologies / FIT-IT research calls opening...Invited talk at Future Networked Technologies / FIT-IT research calls opening...
Invited talk at Future Networked Technologies / FIT-IT research calls opening...Paolo Massa
 
Trustlet, Open Research on Trust Metrics
Trustlet, Open Research on Trust MetricsTrustlet, Open Research on Trust Metrics
Trustlet, Open Research on Trust MetricsPaolo Massa
 
An API of One's Own: Individual Identities as First-Class Citizens in the Ope...
An API of One's Own: Individual Identities as First-Class Citizens in the Ope...An API of One's Own: Individual Identities as First-Class Citizens in the Ope...
An API of One's Own: Individual Identities as First-Class Citizens in the Ope...Nate Otto
 
Recsys virtual-profiles
Recsys virtual-profilesRecsys virtual-profiles
Recsys virtual-profilesHaishan Liu
 
Recsys virtual-profiles
Recsys virtual-profilesRecsys virtual-profiles
Recsys virtual-profilesHaishan Liu
 

Similar to Ithet (20)

Fine-Grained Trust Assertions for Privacy Management in the Social Semantic Web
Fine-Grained Trust Assertions for Privacy Management in the Social Semantic WebFine-Grained Trust Assertions for Privacy Management in the Social Semantic Web
Fine-Grained Trust Assertions for Privacy Management in the Social Semantic Web
 
Social Recommender Systems Tutorial - WWW 2011
Social Recommender Systems Tutorial - WWW 2011Social Recommender Systems Tutorial - WWW 2011
Social Recommender Systems Tutorial - WWW 2011
 
Social Network Analysis (SNA) and its implications for knowledge discovery in...
Social Network Analysis (SNA) and its implications for knowledge discovery in...Social Network Analysis (SNA) and its implications for knowledge discovery in...
Social Network Analysis (SNA) and its implications for knowledge discovery in...
 
Presentation for Doctoral Consortium at UMAP'11
Presentation for Doctoral Consortium at UMAP'11Presentation for Doctoral Consortium at UMAP'11
Presentation for Doctoral Consortium at UMAP'11
 
An Unsupervised Approach For Reputation Generation
An Unsupervised Approach For Reputation GenerationAn Unsupervised Approach For Reputation Generation
An Unsupervised Approach For Reputation Generation
 
Show me the data! Actionable insight from open courses
Show me the data! Actionable insight from open coursesShow me the data! Actionable insight from open courses
Show me the data! Actionable insight from open courses
 
Building Communities of “Trust”
 Building Communities of “Trust” Building Communities of “Trust”
Building Communities of “Trust”
 
Who gives a tweet
Who gives a tweetWho gives a tweet
Who gives a tweet
 
“I Like” - Analysing Interactions within Social Networks to Assert the Trustw...
“I Like” - Analysing Interactions within Social Networks to Assert the Trustw...“I Like” - Analysing Interactions within Social Networks to Assert the Trustw...
“I Like” - Analysing Interactions within Social Networks to Assert the Trustw...
 
Trust blueprints icds 2014
Trust blueprints icds 2014Trust blueprints icds 2014
Trust blueprints icds 2014
 
Personalizing the web building effective recommender systems
Personalizing the web building effective recommender systemsPersonalizing the web building effective recommender systems
Personalizing the web building effective recommender systems
 
Brightspace Analytics, Insights, and Data
Brightspace Analytics, Insights, and DataBrightspace Analytics, Insights, and Data
Brightspace Analytics, Insights, and Data
 
iSpot Analysed: Participatory Learning and Reputation
iSpot Analysed: Participatory Learning and ReputationiSpot Analysed: Participatory Learning and Reputation
iSpot Analysed: Participatory Learning and Reputation
 
IRJET- Web User Trust Relationship Prediction based on Evidence Theory
IRJET- Web User Trust Relationship Prediction based on Evidence TheoryIRJET- Web User Trust Relationship Prediction based on Evidence Theory
IRJET- Web User Trust Relationship Prediction based on Evidence Theory
 
AIST 2015 Conference Paper Presentation
AIST 2015 Conference Paper PresentationAIST 2015 Conference Paper Presentation
AIST 2015 Conference Paper Presentation
 
Invited talk at Future Networked Technologies / FIT-IT research calls opening...
Invited talk at Future Networked Technologies / FIT-IT research calls opening...Invited talk at Future Networked Technologies / FIT-IT research calls opening...
Invited talk at Future Networked Technologies / FIT-IT research calls opening...
 
Trustlet, Open Research on Trust Metrics
Trustlet, Open Research on Trust MetricsTrustlet, Open Research on Trust Metrics
Trustlet, Open Research on Trust Metrics
 
An API of One's Own: Individual Identities as First-Class Citizens in the Ope...
An API of One's Own: Individual Identities as First-Class Citizens in the Ope...An API of One's Own: Individual Identities as First-Class Citizens in the Ope...
An API of One's Own: Individual Identities as First-Class Citizens in the Ope...
 
Recsys virtual-profiles
Recsys virtual-profilesRecsys virtual-profiles
Recsys virtual-profiles
 
Recsys virtual-profiles
Recsys virtual-profilesRecsys virtual-profiles
Recsys virtual-profiles
 

Ithet

  • 1. Trust-Based Rating Prediction for Recommendation in Web 2.0 Collaborative Learning Social Software ITHET 29th April – 1st May 2010, Cappadocia, Turkey Na Li, Sandy El Helou, Denis Gillet Real-Time Coordination and Distributed Interaction Systems (ReAct) Automatic Control Lab, Swiss Federal Institute of Technology in Lausanne
  • 2. Outline Introduction Collaborative Learning Domain 3A Interaction Model Trust-Based Rating Prediction Approach Evaluation and Results Conclusion and Future Work
  • 3. Introduction Web 2.0 social software A large amount of user generated content New challenge: selection of useful resources RSS Feeds Pictures Pictures Wiki Pages Documents Videos
  • 4. Introduction Rating systems Evaluate quality of content in open environment Provide recommendation for different users
  • 5. Introduction Rating systems – application level Rating systems – academic research level TidalTrust (J. Golbeck), MoleTrust(P. Massa) User explicitly specifies a trust value towards another user Build trust network, Random walk in trust network Personalized rating prediction
  • 6.
  • 8.
  • 9.
  • 10. Trust-Based Rating Prediction Approach Direct trust (DT): derived from a particular type of relationship W (Membership): weight of “membership” relationship N (Alice, Membership): number of group activities Alice joins Is Member of Advanced Algorithms Group Activity Alice
  • 11. Trust-Based Rating Prediction Approach Trust propagation Propagation distance (PD) Bob Commented by Article Rated by Sara Create Is Member Has Member French Learning Activity Luis Alice Rate Video Rated by Ben Created by Jack Propagate Propagate Propagate PD
  • 12. Trust-Based Rating Prediction Approach Indirect Trust (IT) Inference
  • 13. Trust-Based Rating Prediction Approach Rating prediction from a user to an item Using user’s “Web of Trust” People in “Web of Trust” are seen as trustable Average of all the rating scores given by trustable people, weighted by their trust value
  • 14. Evaluation and Results Using Remashed data set 50 users, 6000 items, 3000 tags and 450 ratings “Leave-one-out” method Compare “predicted score – actual score” deviation of trust-based prediction and simple average
  • 15. Evaluation and Results Change parameters Weights for relationships doesn’t make a significant difference in rating prediction Increasing size of trust network might add noise, lead to bigger prediction error
  • 16. Conclusion and Future Work Propose a trust-based rating prediction approach, inferring trust in an implicit way Provide personalized rating prediction so as to evaluate user-generated content in collaborative learning environment Future deploy and evaluation will be conducted in a collaborative learning platform, namely Graaasp(graaasp.epfl.ch)

Editor's Notes

  1. Trust propagates layer by layer, until reaching the propagate distance we predefine.A “Web of Trust” is constructed in this way.
  2. Different weights and propagate distances are tried.On this test set, the change of trust weights for relationships doesn’t make a significant difference in the results of rating prediction.We get an optimal propagate distance value, which indicates that, instead of improving the prediction results, increasing the size of trust network might add noise, leading to bigger prediction error.
  3. Different weights and propagate distances are tried.On this test set, the change of trust weights for relationships doesn’t make a significant difference in the results of rating prediction.We get an optimal propagate distance value, which indicates that, instead of improving the prediction results, increasing the size of trust network might add noise, leading to bigger prediction error.