live social semantics @ iswc2009
DESCRIPTION
Paper presented at the International Semantic Web Conference (ISWC) 2009TRANSCRIPT
Live Social Semantics
Martin SzomszorUniversity of Southampton
A novel application that integrates data from the semantic web, online social
networks, and a real-world face-to-face contact sensing platform.
Outline
• History– Where Live Social Semantics came from
• LSS Architecture– Tracking Face-to-Face Contacts– Integrating and Managing Data– Building Profiles of Interest
• Video Demonstration• LSS at ESWC2009• Future Work
Live Social Semantics
• History– Dagstuhl Seminar on Social Web Communities
(Sept 2008)
Sociopatterns.org
http://www.sciencegallery.com/infectious
This 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.
Southampton
• Automatic 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.
ISI (Turin) Meeting March 2009
LSS – Proposed Features• Contact 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”
Features NOT Required• We 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 area
Participation• Participation is voluntary• Association of your RFID badge to your real
identity is voluntary– You can participate using only an anonymous id
LSS Stack
Live Social Semantics
Web2.0 Linked DataDelicious
Real World
semanticweb.org
acm, dblp, citeseer …
rkbexplorer.com
Active RFID Contact Tracking
Local Server
ESWC2009 Map
Active RFID Proximity Detection
• spatial resolution ~ 1 meter• anisotropy - face-to-face• temporal resolution ~ 5-20 seconds• unobtrusive• scalable– low cost (~15 Euro per badge – reusable)– easily deployable– distributed
RDF Representation of Contact Data
http://tagora.ecs.soton.ac.uk/LiveSocialSemantics/eswc2009/1410
http://tagora.ecs.soton.ac.uk/LiveSocialSemantics/eswc2009/contact/day3/1410/1515
http://tagora.ecs.soton.ac.uk/LiveSocialSemantics/eswc2009/1515
hasPhysicalContact
"2009-06-03"^^<http://www.w3.org/2001/XMLSchema#date>
"00:01:43"^^<http://www.w3.org/2001/XMLSchema#time>
contactWith
contactDate
contactDuration
Social Semantics
ArchitectureW
eb B
ased
Sys
tem
sRe
al W
orld
4store
ExtractorDaemon
Delicious
Flickr
Lastfm
Facebook Connect API
RKBExplorer.com
data.semanticweb.org
ProfileBuilder
dbtune.org
dbpedia.org
TAGora SenseRepository
COP + Publications
Publications
Social TaggingSocial Networks
Contacts
mbid - > dbpedia uritag -> dbpedia uri
Loca
l Ser
ver
Aggr
egat
or
RDF
Cach
eRFID Readers
RFID Badges
Real World Contact Data
ConsumesTagging Data
Returns Profileof Interests
How are you connected?
Delicious
Folksonomies, The Semantic Web, and Movie Recommendation
Live Social Semantics
www.tagora-project.eu
Publications
Projects
CiroCattuto
MartinSzomszor
Distinct, Separated Identity Management
http://tagora.ecs.soton.ac.uk/delicious/martinszomszor
http://tagora.ecs.soton.ac.uk/flickr/7214044@N08@N08
http://tagora.ecs.soton.ac.uk/lastfm/count-bassy
http://tagora.ecs.soton.ac.uk/facebook/613077109
MartinSzomszor
http://data.semanticweb.org/person/martin-szomszor/
http://southampton.rkbexplorer.com/id/person-05877
http://tagora.ecs.soton.ac.uk/LiveSocialSemantics/eswc2009/1410
http://tagora.ecs.soton.ac.uk/LiveSocialSemantics/eswc2009/foaf/1
Delicious Tagging and Network
Flickr Tagging and Contacts
Lastfm favourite artists and friends
Facebook contacts
RFID Contact Data
Conference Publication Data
Past Publications, Projects, Communities of Practice
Profiles of Interest
http://tagora.ecs.soton.ac.uk/LiveSocialSemantics/eswc2009/foaf/1
foaf:Person
http://tagora.ecs.soton.ac.uk/delicious/martinszomszor
foaf:Persontagging:Tagger
http://tagora.ecs.soton.ac.uk/delicious/tag/ontologymapping
tagging:UserTag
http://tagora.ecs.soton.ac.uk/tag/ontologymapping
tagging:GlobalTag
http://dbpedia.org/resource/Semantic_Integration
TAGora Sense Repository
tagging:UsesTag
owl:SameAs
tagging:hasGlobalTag
disam:hasPossibleSense
foaf:interest
Profile Building• 1) Disambiguate Tags– cosine similarity between user co-occurrence vector
and term frequency vector from concept– Choose Sense if above threshold (0.3) or single sense
• 2) Calculate Interest Weights– weight 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 List– If more than 50 interests are suggested, we rank by
weight and suggest the top 50– Users must verify the list before it is published
Live Social Semantics Videohttp://vimeo.com/6590604
LSS @ ESWC2009
• 4 Days (1-4 June 2009)• >300 Attendees, 187 of which participated in the
experiment• Each participant was issued with a uniquely
number RFID badge• Users could register their badge number on a
website, and associate it to their name, institution, email, and social networking accounts
• Out of the 187 who collected a badge, 139 registered their account on the website
SNS Usage Statistics
ESWC 09total 187
registered 139 (74%)Flickr 52 (37%)
Delicious 59 (42%)Last.FM 57 (41%)Facebook 78 (56%)
Survey Results
Option Reason No. Users %
a don’t have those accounts (or rarely use them) 9 41%
b use different networking sites 4 18%
c don’t like to share them 2 9%
d didn’t get a chance to share them (e.g. no computer, slow internet)
6 27%
e other 1 5%
TOTAL 22 100%
After 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:
Future Work• Allow individuals to link to their own foaf
profiles• More SNS sites:– Twitter, LinkedIn, etc…
• Document and Advertise Linked Data Interface– Support other applications in exploiting the data
• Recommend Contacts– What features are most predictive of face-to-face
contact
Building Better Profiles
• What tags correspond to interests?– Locations and topics are useful, but other terms
are not• TF / IDF Approach– It’s not that useful to find out we are all interested
in RDF and the Semantic Web• Making use of the Category hierarchy– If I’m interested in Facebook, Flickr, Last.fm,
Delicious, etc, I can extrapolate the interest Online_Social_Networks
University of Southampton
Ciro Cattuto, Wouter Van den Broeck, Alain Barrat
Harith Alani, Martin Szomszor, Gianluca Correndo
Acknowledgements
Thanks for your attention
Presence of Attendees HT2009
Number of cliques HT2009