An Exploratory Study on Using Social Information Networks for Flexible Literature Access
3 likes1,011 views
This document presents an exploratory study on using social information networks to enhance literature access, proposing a model that incorporates social factors such as author importance and relevance features. It discusses the methodology for integrating social relevance with traditional information retrieval processes, providing experimental evaluations of the proposed model. The conclusion emphasizes the need for further research on the effectiveness of social content graphs and the adjustment of social relationships in retrieval systems.
![About Social Information RetrievalIncorporating information from social network in the information retrieval processAccess to relevant information in the social neighborhoodSpread information through the social networkTake account of the social activity Crossing two domains [KIRSCHet al , 2003]Information RetrievalRepresent and compare document /querySocial Network Analysis [WESSERMANN & FAUST]Represent social entities and relationshipsEstimate individual’s centrality5Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook](https://image.slidesharecdn.com/anexploratorystudyonusingsocialinformation-100119100119-phpapp01/85/An-Exploratory-Study-on-Using-Social-Information-Networks-for-Flexible-Literature-Access-5-320.jpg)
![About Social Information RetrievalSocial relevance features [AMER & al, 07] Topical relevanceSocial distanceIncoming links and bookmarksTimeliness and freshnessSocial importance of individualsRelevant documents are published by important people6Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook](https://image.slidesharecdn.com/anexploratorystudyonusingsocialinformation-100119100119-phpapp01/85/An-Exploratory-Study-on-Using-Social-Information-Networks-for-Flexible-Literature-Access-6-320.jpg)
![About Social Information RetrievalDomain application of Social Information RetrievalKnowledge and experience sharing , Collaborative production [KORFAITIS & al, 2006]Wiki, SourgeForgeOpinion retrieval [ZANG & YE, 2008]BlogsSocial media and bookmarking [HEYMANN & al, 2008] [BUDURA & al, 2008]Facebook, YouTube, Del.ici.usInformation finding and social network exploring [ZANG & al , 2008]Social ranking of document, Expert searchingLiterature access [KIRSCH & al , 2006]CiteULike.org7Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook](https://image.slidesharecdn.com/anexploratorystudyonusingsocialinformation-100119100119-phpapp01/85/An-Exploratory-Study-on-Using-Social-Information-Networks-for-Flexible-Literature-Access-7-320.jpg)
![Literature AccessIndexing scientific publicationAccess to content and metadataIntegrate heterogeneous bibliographic resourcesExplore citationRanking publication Content featureCitation feature [EDGAR & RIJIKE, 07] Citation analysis in information retrievalExtracting terms form citing documentsConsidering citation as hyperlinks8Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook](https://image.slidesharecdn.com/anexploratorystudyonusingsocialinformation-100119100119-phpapp01/85/An-Exploratory-Study-on-Using-Social-Information-Networks-for-Flexible-Literature-Access-8-320.jpg)
![Related worksExtract social network form bibliographic resources [KIRSCH, 2003] [MUTSCHKE, 2001] [KIRCHNOFF & al, 2008] Actors : documents and authorsEdges : co-author relationshipsMultiplicative relevance score [KIRSCH, 2003] Query document similarityAuthor’s authority9Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook](https://image.slidesharecdn.com/anexploratorystudyonusingsocialinformation-100119100119-phpapp01/85/An-Exploratory-Study-on-Using-Social-Information-Networks-for-Flexible-Literature-Access-9-320.jpg)
![Social Importance measures [KIRCHNOFF & al, 08] [LANGVILLE & MEYR, 08] Rank nodes according to their position in the networkEstimate document relevanceDegreeSocial activity](https://image.slidesharecdn.com/anexploratorystudyonusingsocialinformation-100119100119-phpapp01/85/An-Exploratory-Study-on-Using-Social-Information-Networks-for-Flexible-Literature-Access-13-320.jpg)
An Exploratory Study on Using Social Information Networks for Flexible Literature Access
- 1. An exploratory study on using social informationnetworks for flexible literature accessLynda Tamine, Amjed Ben Jabeur and WahibaBahsounUniversity Paul Sabatier Toulouse III, FranceIRIT SIG-RI{lechani, jabeur,wbahsoun}@irit.frFQAS 2009
- 2. An exploratory study on using social information networks for flexible literature accessOutline:Social Information Retrieval : Background and motivationA social based model for literature accessExperimental evaluationConclusion and outlook2
- 3. Towards Social Information RetrievalIRSQueryUserProfileTagComment3Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook
- 4. Towards Social Information RetrievalInformation ProducerDocumentsSocial Information RetrievalQueriesInformation consumerTags, comments ..etc4Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook
- 5. About Social Information RetrievalIncorporating information from social network in the information retrieval processAccess to relevant information in the social neighborhoodSpread information through the social networkTake account of the social activity Crossing two domains [KIRSCHet al , 2003]Information RetrievalRepresent and compare document /querySocial Network Analysis [WESSERMANN & FAUST]Represent social entities and relationshipsEstimate individual’s centrality5Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook
- 6. About Social Information RetrievalSocial relevance features [AMER & al, 07] Topical relevanceSocial distanceIncoming links and bookmarksTimeliness and freshnessSocial importance of individualsRelevant documents are published by important people6Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook
- 7. About Social Information RetrievalDomain application of Social Information RetrievalKnowledge and experience sharing , Collaborative production [KORFAITIS & al, 2006]Wiki, SourgeForgeOpinion retrieval [ZANG & YE, 2008]BlogsSocial media and bookmarking [HEYMANN & al, 2008] [BUDURA & al, 2008]Facebook, YouTube, Del.ici.usInformation finding and social network exploring [ZANG & al , 2008]Social ranking of document, Expert searchingLiterature access [KIRSCH & al , 2006]CiteULike.org7Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook
- 8. Literature AccessIndexing scientific publicationAccess to content and metadataIntegrate heterogeneous bibliographic resourcesExplore citationRanking publication Content featureCitation feature [EDGAR & RIJIKE, 07] Citation analysis in information retrievalExtracting terms form citing documentsConsidering citation as hyperlinks8Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook
- 9. Related worksExtract social network form bibliographic resources [KIRSCH, 2003] [MUTSCHKE, 2001] [KIRCHNOFF & al, 2008] Actors : documents and authorsEdges : co-author relationshipsMultiplicative relevance score [KIRSCH, 2003] Query document similarityAuthor’s authority9Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook
- 10. ContributionRelationships extracted from bibliographic resources :Co-authorshipCitation linkLinear combinationTopical relevanceSocial importance of documentsStudy the impact of centrality measures10Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook
- 11. Social Content Grapha1a3a2a4a6a1a3a4a2a5Co-authord1d2d3d4CitationSocial network graphV: Authors E: Relationships between authorsAn edge express: Co-auteur relationship (implicit direct)Citation relationship (implicit indirect)11Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook
- 12. Estimate document relevanceStep 1. Social Importance of authorsa1a3a4a2Ranked ListSocialImportanceAlgorithmsOf authorsDegree, Closeness, BetweenessPageRank and Hits{author, score}Social NetworkSocial Network AnalysisSocial Scores12Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook
- 13. Social Importance measures [KIRCHNOFF & al, 08] [LANGVILLE & MEYR, 08] Rank nodes according to their position in the networkEstimate document relevanceDegreeSocial activity
- 14. Popularity
- 16. InfluenceBetweenssInterdisciplinaryPageRankAuthorityHitsHub and authority13Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook
- 17. Step 2. From author score to document social importanceEstimate document relevanceC(v2)C(v1) Sum of the authors social scores
- 18. Implicitly taking account of the number of co-authors
- 20. Weighted Sum, Min, Max, AVG …etcImp(d)C(v4)C(v3)14Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook
- 21. Estimate document relevanceStep 3. Retrieving documentsStep 4. Combining topical relevance and social importanceResult setIRSQuery{d, RSV (q,d)}Topical relevanceSocial importance15Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook
- 22. ACM SIGIR 1978-2008Metadata gathered from ACM Portal AuthorCitations linksDownloads ( Mars 2008 – Mars 2009)ExperimentationDegree distributionVerticeswithdegreeδ(ν)Vertex degreeδ(ν)16Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook
- 23. ExperimentationChoosing queriesExperimentation measureSIGIRCollection50 QueriesTop 50 DocsMost cited assumption-------------
- 24. -------------
- 25. -------------
- 26. -------------
- 27. -------------
- 28. -------------
- 29. -------------
- 30. -------------
- 31. -------------
- 32. -------------1{titleterms}Most downloaded assumption2Known item retrieval{ d,q }50 x{ d, q, rank }50 x { document, query}17Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook
- 33. Comparing importance measuresMost cited assumptionMost downloaded assumptionCo-authorCitationCo-author & Citation18Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook
- 34. Parameter TuningMost cited assumptionPageRankPageRankHITSClosenessMost downloaded assumptionCo-author & CitationCo-authorCo-authorCitationCo-author & CitationCitation19Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook
- 35. Comparative evaluationCo-author 27% 0.212 0.270 26% 59% Most cited 27% 61% Most citedCitation 59% 59% Co-author & Citation 61% 61% 20Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook
- 36. ConclusionA social network based information access model Co-author and citation relationshipsLinear combination of scoresStudy effectiveness of the model using several social importance measureEnsure the soundness of our results using two social relevance assumptions21Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook
- 37. OutlookExtend the social content graphAdditional relationshipsWeighting social relationshipsInclude tag entityTest our retrieval model on a large web collectionStudy recall and precision of the proposed approach22Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook
- 38. Thanks for your attention !
- 39. References[KIRSH & al, 06] Sebastian Kirsch, Melanie Gnasa, Armin Cremers,“Beyond the Web : Retrieval in Social Information Spaces” , Proceedings of the 28th European Conference on Information Retrieval, ECIR 2006, Imperial College, London, 2006[AMER & al, 07] SihemAmer-Yahia, Michael Benedikt,Philip Bohannon, “Challenges in Searching Online Communities” , IEEE Data Eng. Bull., 2007[KIRCHNOFF & al, 08] Lars Kirchhoff, Katarina Stanoevska-Slabeva, Thomas Nicolai and Matthes Fleck , “Using social network analysis to enhance information retrieval systems , Applications of Social Network Analysis”, ASNA, Zurich, 2008[LANGVILLE & MEYR, 08] Lars Kirchhoff, Katarina Stanoevska-Slabeva, “Using social network analysis to enhance information retrieval systems , Applications of Social Network Analysis”, ASNA, Zurich, 200824Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook
- 40. References[MUTSCHKE, 01] Peter Mutschke, “Enhancing Information Retrieval in Federated Bibliographic Data Sources Using Author Network Based Stra-tagems”, Reserach and Advanced Technology for Digital Libraries : 5th European Conference, ECDL 2001, Darmstadt, Germany, September 4-9, 2001[EDGAR & RIJIKE, 07] Edgar Meij and Maarten de Rijke,“Using Prior In-formation Derived from Citations in Literature Search”Proceedings of RIAO 2007 : Recherched’InformationAssistée par Ordinateur 2007, 2007[KORFIATIS & al., 2006] Korfiatis, N.; Poulos, M. & Bokos, G. “EvaluatingAuthoritative Sources using Social Networks: An Insight fromWikipedia”, Online Information Review, 2006, 30, 252-262 [HEYMANN & al, 2008] Paul Heymann, Daniel Ramage, Hector G. Molina "Social tag prediction Export" In SIGIR '08: Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval (2008), pp. 531-538.25Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook
- 41. References[BUDURA et al.] Adriana Budura, Sebastian Michel, Philippe C. Mauroux, Karl Aberer “ To tag or not to tag -: harvesting adjacent metadata in large-scaletaggingsystemsExpor ”, In SIGIR '08: Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval (2008), pp. 733-734. [ZHANG et al.] Jing Zhang, Jie Tang and Juanzi Li “ Expert Finding in a Social Network ”, Advances in Databases: Concepts, Systems and Applications, Volume 4443/2008, 1066-1069, Springer Berlin / Heidelberg, 2008[ZANG & YE, 2008 ] Min Zhang and XingyoaYe “ A generation model to unifytopic relevance and lexicon-based sentiment for opinion retrieval ”, In Proceedings of the 31st Annual international ACM SIGIR Conference on Research and Development in information Retrieval (Singapore, Singapore, July 20 - 24, 2008). SIGIR '08. ACM, New York, NY, 411-41826Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook
- 42. References[WASSERMAN & KHATERINE] Stanley Wasserman and Katherine Faust “ Social network analysis: methods and applications”,Cambridge Uni. Press[KIRSCH, 2003] Sebastian Marius Kirsch, “ Social information retrieval ”, PhDThesis in Computer Science, Computer science department III, Bonn, 14 March 2003 [KIRSCH & al. , 2006] Sebastian Kirsch, MelanieGnasa, and Armin Cremers “ Beyondthe web: Retrieval in social information spaces”,EuropeanConference on IR Research No28, London , ROYAUME-UNI (2006) 2006 [RITCHIE & TEUFEL, 2007] Anna Ritchie, Simone Teufel and Stephen Robertson, “ Usingtermsfrom citations for IR: some first results”,Proceedings of the EuropeanConference for Information Retrieval ECIR, pp 211-221, 2007[SMALL, 1973] Henry Small “ Co-citation in the scientificliterature: A new measurement of the relationshipbetweentwodocuments”,Journal of the American Society of Information27Background and motivation | Social based model for literature access | Experimental evaluation | Conclusion and outlook