• Save
ESWC 2014 Tutorial part 2
Upcoming SlideShare
Loading in...5

ESWC 2014 Tutorial part 2



ESWC 2014 Tutorial part 1 http://tutorials.oeg-upm.net/socialweb/

ESWC 2014 Tutorial part 1 http://tutorials.oeg-upm.net/socialweb/



Total Views
Views on SlideShare
Embed Views



0 Embeds 0

No embeds



Upload Details

Uploaded via as Adobe PDF

Usage Rights

© All Rights Reserved

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
Post Comment
Edit your comment

ESWC 2014 Tutorial part 2 ESWC 2014 Tutorial part 2 Presentation Transcript

  • Social Web: Where are the Semantics? ESWC 2014 Miriam Fernández, Victor Rodríguez, Andrés García-Silva, Oscar Corcho Ontology Engineering Group, UPM, Spain Knowledge Media Institute, The Open University
  • Outline 2 •  Part 1: Understanding Social Media –  Theory: background & applications described in this tutorial –  Hands on: data extraction from Twitter and Facebook •  Part 2: Using semantics to represent data from SNS –  Theory: Using SW to represent content, users and relations –  Hands on: applying and extending SIOC •  Part 3: Using semantics to understand social media conversations –  Theory: Using semantics to understand topics in social media –  Hands on: using LDA to extract topics from social media •  Part 4: Using semantics to understand user behaviour
  • Using the SW to represent data from SNS •  Social data is contained in silos –  Distributed identities –  Heterogeneous formats –  Isolated communities ESWC 2014 Social Web: Where are the Semantics? 3
  • Using the SW to represent data from SNS –  Data unification •  Each SNS contains data in a different format (heterogeneity) •  Difficult to access information in a unified way across SNS •  Real and emergent need to develop portable analysis models –  Data integration •  The same user can participate in different SNS / communities •  The same topic can be discussed in different SNS / communities –  Data interpretation •  Data -> information -> knowledge •  Find ways in which machines can interpret social media content –  Better Information Retrieval –  Better Recommendation –  Data liberation •  Export your data in a common format! ESWC 2014 Social Web: Where are the Semantics? 4
  • Using the SW to represent data from SNS •  Use common, shared ontologies to represent –  People –  Relationships –  Social objects (content) ESWC 2014 Social Web: Where are the Semantics? 5 Demographic characteristics Preferences Social Network Online Communities Behaviour Personality Content The User Needs SUM SUM MESHOUBO FOAF Schema.org Microformats SemSNA SIOC Schema.org FOAF MESH Domain- specific PAO SIOC SIOC These are not the only ones, explore! ;)
  • The User / Social Networks: FOAF •  Class foaf:Person –  foaf:name –  foaf:gender –  foaf:birthday –  foaf:homepage 6 <foaf:Person rdf:about="http://www.miriamfs.com/foaf/foaf.rdf#me"> <foaf:name>Miriam Fernandez</foaf:name> <foaf:title>Dr</foaf:title> <foaf:givenname>Miriam</foaf:givenname> <foaf:family_name>Fernandez</foaf:family_name> <foaf:nick>miriam.fs</foaf:nick> <foaf:knows> <foaf:Person> <foaf:name>Victor Rodriguez</foaf:name> </foaf:Person> </foaf:knows> http://xmlns.com/foaf/spec/ It describes people and their relations (i.e., their social network)
  • Online Communities: SIOC •  Class: sioc:UserAccount –  sioc:id –  sioc:name –  dc:created –  sioc:creator_of –  foaf:knows •  Class: siocPost –  sioc:content –  dc:created –  sioc: has_creator –  sioc:has_parent –  sioc:num_views 7 •  Class: siocThread –  sioc:parent_of –  sioc: has_creator –  sioc:has_parent •  Class: Container –  sioc:parent_of –  sioc:has_host http://sioc-project.org/ It describes online communities, including people, their social network and the content they produce
  • Online Communities: SIOC ESWC 2014 Social Web: Where are the Semantics? Image extracted from: http://sioc-project.org/
  • Behaviour: OUBO •  sioc: UserAccount –  oubo:hasRole •  oubo: UserImpact –  oubo:initation –  oubo:contribution –  oubo:engagement –  oubo:popularity 9 •  oubo:Role –  oubo:inColaborative Environment –  oubo:inTimeFrame –  oubo:userImpact –  oubo:has_user_account http://purl.org/net/oubo/0.3 Extends the SIOC ontology to represent user behaviour according to his/her context: place (online community) and time Angeletou et. al. Modelling and Analysis of User Behaviour in Online Communities. ISWC 2011
  • Preferences: MESH •  foaf:Person –  mesh:semanticInterests –  mesh:itemRatings •  mesh:SemanticInterests –  mesh:semanticInterest •  mesh:ItemRatings –  mesh:itemRating 10 •  mesh:WeightedConcept –  mesh:weight –  mesh:concept •  mesh:ItemRating –  mesh:ratingCriterium –  mesh:interestSituation –  mesh:ratingValue –  mesh:timestamp –  mesh:ratedItem one or more http://www.mesh-ip.eu The MESH ontology models the user, his social network and his preferences (ratings as well as semantic preferences) Cantador et. al. A Multi-Purpose Ontology- Based Approach for Personalised Content Filtering and Retrieval
  • User Needs: SUM •  foaf:Person –  swum:hasNeeds •  swum: UserNeeds •  swum:Entretainment •  swum:EsteemNeeds •  swum:SelfActualization •  swum:SocialNeeds 11 Different types of user needs are modelled as classes. Maslow’s pyramid of needs http://swum-ontology.org/ont/swum.owl Models the user and his needs
  • Personality: PAO •  pao:Personality •  pao:PersonalityDimension •  pao:Agreebleness •  pao:Conscientiusness •  Pao:Extraversion •  Pao:Neuroticisim 12 •  Personality dimensions are modelled as classes and subclasses Donohue et. al. THE FIVE-FACTOR MODEL AND PERSONALITY ASSESSMENT ONTOLOGY
  • Hands on: Using SIOC to model Twitter Data ESWC 2014 Social Web: Where are the Semantics? 13 sioc:reply_of/ sioc:has_reply sioct: Microblog Post Tweet URL sioc:content Tweet Text dcterms:created Tweet creation time sioc:has_container/ sioc:container_of sioct: Microblog sioc:has_creator/ sioc:creator_of sioc:UserAccount sioc:name Screen name sioc:has_space/ sioc:space_of sioc:Site Twitter homepage sioc:topic sioct:Tag sioc:name Extracted hashtag sioc:links_to Extracted link sioc:mentions sioc:follows sioc:subscriber_of/ sioc:has_subscriber, sioc:isPartOf/ sioc:hasPart sioc:has_owner/ sioc:owner_of geo:long Tweet Longt. geo:lat Tweet Lat. gn:Feature sioc:about ... geo:Point geo:location dcterms:created Account creation time sioc:note Account description sioc:avatar Avatar URL User Twitter homepage User ID dcterms:title User name sioc:forwarded_by sioc:Container Twitter list ID sioc:addressed_to •  How to model re- tweets? •  How to model lists?