Live Social Semantics @ ISWC2009
Download as PPTX, PDF0 likes486 views
This document summarizes a novel application called Live Social Semantics that integrates data from the semantic web, online social networks, and an RFID-based face-to-face contact sensing platform. It tracks face-to-face contacts between conference attendees using RFID badges, builds profiles of attendees' interests by linking their social media data, and allows attendees to view their connections to other attendees. The system was tested at a conference where over 300 attendees participated, and future work is proposed to improve interest profiling and support additional applications using the social interaction data.
![SouthamptonAutomatic Generation of Profiles of Interest using Cross-Folksonomy Data[2] Szomszor, M., Alani, H., Cantador, I., O'Hara, K. and Shadbolt, N. (2008) Semantic Modelling of User Interests based on Cross-Folksonomy Analysis. In: 7th International Semantic Web Conference (ISWC), October 26th - 30th, Karlsruhe, Germany.](https://image.slidesharecdn.com/iswc2009-lss-100727120545-phpapp02/85/Live-Social-Semantics-ISWC2009-5-320.jpg)
Live Social Semantics @ ISWC2009
- 1. Live Social SemanticsA novel application that integrates data from the semantic web, online social networks, and a real-world face-to-face contact sensing platform.Martin SzomszorUniversity of Southampton
- 2. OutlineHistoryWhere Live Social Semantics came fromLSS ArchitectureTracking Face-to-Face ContactsIntegrating and Managing DataBuilding Profiles of InterestVideo DemonstrationLSS at ESWC2009Future Work
- 3. Live Social SemanticsHistoryDagstuhl Seminar on Social Web Communities (Sept 2008)
- 4. Sociopatterns.orgThis projects aims to shed light on patterns in social dynamics and coordinated human activity. We do so by developing and deploying an experimental social interaction sensing platform. This platform consists of portable sensing device and software tools for aggregating, analyzing and visualizing the resulting data.http://www.sciencegallery.com/infectious
- 5. SouthamptonAutomatic Generation of Profiles of Interest using Cross-Folksonomy Data[2] Szomszor, M., Alani, H., Cantador, I., O'Hara, K. and Shadbolt, N. (2008) Semantic Modelling of User Interests based on Cross-Folksonomy Analysis. In: 7th International Semantic Web Conference (ISWC), October 26th - 30th, Karlsruhe, Germany.
- 6. ISI (Turin) Meeting March 2009
- 7. LSS – Proposed FeaturesContact Histories“Hey, I remember talking to this person, but I don’t know their name / email / institution”People you might know “Who are the people in my social networks / community of practice who are also attending the conference? What papers are they presenting”Profiles of Interest“I’d like to expose the things that I’m interested in to other participants, including extra-academic data”
- 8. Features NOT RequiredWe are not concerned with tracking an individual’s exact location. The focus of LSS is to log social interactions (face-to-face contact)We don’t want to track people outside the conference areaParticipationParticipation is voluntary
- 9. Association of your RFID badge to your real identity is voluntary
- 10. You can participate using only an anonymous idLSS StackLive Social SemanticsWeb2.0Linked DataReal WorldDelicioussemanticweb.orgrkbexplorer.comacm, dblp, citeseer …
- 11. Active RFID Contact TrackingLocal Server
- 12. ESWC2009 Map
- 13. Active RFID Proximity Detectionspatial resolution ~ 1 meteranisotropy - face-to-facetemporal resolution ~ 5-20 secondsunobtrusivescalablelow cost (~15 Euro per badge – reusable)easily deployabledistributed
- 14. RDF Representation of Contact Datahttp://tagora.ecs.soton.ac.uk/LiveSocialSemantics/eswc2009/1410http://tagora.ecs.soton.ac.uk/LiveSocialSemantics/eswc2009/1515hasPhysicalContactcontactWithhttp://tagora.ecs.soton.ac.uk/LiveSocialSemantics/eswc2009/contact/day3/1410/1515"2009-06-03"^^<http://www.w3.org/2001/XMLSchema#date>contactDate"00:01:43"^^<http://www.w3.org/2001/XMLSchema#time> contactDuration
- 15. ArchitectureCOP + PublicationsRKBExplorer.comProfileBuilderdbtune.orgPublicationsdata.semanticweb.orgdbpedia.orgConsumesTagging DataTAGora SenseRepositoryExtractorDaemonDeliciousSocial TaggingSocial NetworksWeb Based SystemsFlickrmbid - > dbpediauritag -> dbpediauriLastfmReturns Profileof InterestsContactsFacebookConnect API4storeRFID ReadersLocal ServerSocial SemanticsRDF CacheAggregatorReal WorldReal World Contact DataRFID Badges
- 16. How are you connected?DeliciousFolksonomies, The Semantic Web, and Movie RecommendationCiroCattutoMartinSzomszorLive Social SemanticsPublicationswww.tagora-project.euProjects
- 17. Distinct, Separated Identity Managementhttp://tagora.ecs.soton.ac.uk/LiveSocialSemantics/eswc2009/foaf/1MartinSzomszorDelicious Tagging and NetworkRFID Contact Datahttp://tagora.ecs.soton.ac.uk/delicious/martinszomszorhttp://tagora.ecs.soton.ac.uk/LiveSocialSemantics/eswc2009/1410Flickr Tagging and ContactsConference Publication Datahttp://tagora.ecs.soton.ac.uk/flickr/7214044@N08@N08http://data.semanticweb.org/person/martin-szomszor/Lastfm favourite artists and friendsPast Publications, Projects, Communities of Practicehttp://tagora.ecs.soton.ac.uk/lastfm/count-bassyhttp://southampton.rkbexplorer.com/id/person-05877Facebook contactshttp://tagora.ecs.soton.ac.uk/facebook/613077109
- 18. Profiles of Interesttagging:hasGlobalTagTAGora Sense Repositorytagging:UserTagtagging:GlobalTaghttp://tagora.ecs.soton.ac.uk/delicious/tag/ontologymappinghttp://tagora.ecs.soton.ac.uk/tag/ontologymappingdisam:hasPossibleSensetagging:UsesTaghttp://dbpedia.org/resource/Semantic_Integrationtagging:Taggerfoaf:Personhttp://tagora.ecs.soton.ac.uk/delicious/martinszomszorfoaf:interestfoaf:Personhttp://tagora.ecs.soton.ac.uk/LiveSocialSemantics/eswc2009/foaf/1owl:SameAs
- 19. Profile Building1) Disambiguate Tagscosine similarity between user co-occurrence vector and term frequency vector from conceptChoose Sense if above threshold (0.3) or single sense2) Calculate Interest Weightsweight w = fr ∗ ur , where fr is the total frequency of all tags disambiguated to sense r, and ur is a a time decay factor. The factor ur = ⌈days(r)/90⌉3) Create Interest ListIf more than 50 interests are suggested, we rank by weight and suggest the top 50Users must verify the list before it is published
- 20. Live Social Semantics Videohttp://vimeo.com/6590604
- 21. LSS @ ESWC20094 Days (1-4 June 2009)
- 22. >300 Attendees, 187 of which participated in the experiment
- 23. Each participant was issued with a uniquely number RFID badge
- 24. Users could register their badge number on a website, and associate it to their name, institution, email, and social networking accounts
- 25. Out of the 187 who collected a badge, 139 registered their account on the website
- 27. Survey ResultsAfter the conference, we emailed the users who did register on our site, but did not enter any social networking accounts. The aim was to understand the reasons why:
- 28. Future WorkAllow individuals to link to their own foaf profilesMore SNS sites:Twitter, LinkedIn, etc…Document and Advertise Linked Data InterfaceSupport other applications in exploiting the dataRecommend ContactsWhat features are most predictive of face-to-face contact
- 29. Building Better ProfilesWhat tags correspond to interests?Locations and topics are useful, but other terms are notTF / IDF ApproachIt’s not that useful to find out we are all interested in RDF and the Semantic WebMaking use of the Category hierarchyIf I’m interested in Facebook, Flickr, Last.fm, Delicious, etc, I can extrapolate the interest Online_Social_Networks
- 30. University of SouthamptonAcknowledgementsCiroCattuto, Wouter Van den Broeck, Alain BarratHarithAlani, Martin Szomszor, GianlucaCorrendo
- 31. Thanks for your attention
- 32. Presence of Attendees HT2009
- 33. Number of cliques HT2009