discovering semantic equivalence of people behind online profiles (red 2012 - eswc 2012)
DESCRIPTION
This paper was presented at the Fifth International Workshop on Resource Discovery (RED 2012: http://www.labf.usb.ve/RED2012/) at ESWC 2012 (http://2012.eswc-conferences.org/) Conference in Heraklion, Crete, Greece on 27 May 2012. The full paper can be found at: http://ceur-ws.org/Vol-862/REDp5.pdfTRANSCRIPT
Copyright 2011 Digital Enterprise Research Institute. All rights reserved.
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
Discovering Semantic Equivalence of People
behindOnline Profiles
Keith Cortis, Simon Scerri, Ismael Rivera, Siegfried Handschuh
REsource Discovery (RED), Workshop at ESWC 2012
27th May 2012
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
Motivation
Current situation: Personal data is
unnecessarily duplicated over different platforms
No possibility to merge or port such data
Separate handling of this data
Social Networking Sites as Walled Gardens – David Simonds
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
Problem Specification
No common standards exist for modelling profile data in online accounts
Personal data (known contacts and presence information) is dynamic and continuously changing
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
Objectives
Aim: User represented through one digital identity
Main Challenge: Discovery of semantic equivalence between contacts described in online profiles
Proposal: Use a comprehensive ontology framework for handling online profile data
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
di.me Ontology Framework
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
Related Work Comparison
Existing Profile Linking Approaches based on:o User’s friendso Specific Inverse Functional Properties (e.g. email
address)o Syntactic matching of all profile attributeso Semantic relatedness between text, depending on
Knowledge Bases (KB) such as Wikipedia Our Approach: Similarity measure based on user’s
Personal Information Model (PIM)
PIM
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
Approach (1)
User Profile Data
Ontology Mapping
Online Profile Resolution
Linguistic Analysis
Semantic Search
Extension
Ontology-enhanced Attribute
Weighting
A
B
D
Matching AttributesC1 3 42
Dire
ct S
trin
g M
atch
ing
Indi
rect
Str
ing
Mat
chin
g
Valu
e M
atch
ing
Syntactic Matching 2
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
Approach (2)
User Profile Data
Ontology Mapping
Online Profile Resolution
Linguistic Analysis
Semantic Search
Extension
Ontology-enhanced Attribute
Weighting
A
B
D
Matching AttributesC1 3 42
Dire
ct S
trin
g M
atch
ing
Indi
rect
Str
ing
Mat
chin
g
Valu
e M
atch
ing
Syntactic Matching 2
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
Approach (3)
User Profile Data
Ontology Mapping
Online Profile Resolution
Linguistic Analysis
Semantic Search
Extension
Ontology-enhanced Attribute
Weighting
A
B
D
Matching AttributesC1 3 42
Dire
ct S
trin
g M
atch
ing
Indi
rect
Str
ing
Mat
chin
g
Valu
e M
atch
ing
Syntactic Matching 2
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
Approach (3)
Identity-related online profile information - NCO
Presence and online post data for the user – DLPO
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
Approach (3)
Account Ontology (DAO) – for modelling service account representations
NCODAODLPO
hasCustomAttribute
Contact
PersonContact
OrganizationContact
nie:DataObject
ContactGroup
belongsToGroup
geo:PointhasLocation
keyphoto
representative
soundblogUrl
foafUrl
hasEmailAddress
hasIMAccount
hasPhoneNumber
hasPostalAddress
websiteUrlrdfs:Resource
EmailAddress
PostalAddress
PhoneNumber
IMAccount
Account
LivePost
MultimediaPost
MessagePresencePost
xsd:string
userIDpassword
Credentials
hasCredentials
NamehasName
rdfs:labelnao:externalIdentifier
rdfs:label
source sourceWebDocumentPost
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
Approach (4)
User Profile Data
Ontology Mapping
Online Profile Resolution
Linguistic Analysis
Semantic Search
Extension
Ontology-enhanced Attribute
Weighting
A
B
D
Matching AttributesC1 3 42
Dire
ct S
trin
g M
atch
ing
Indi
rect
Str
ing
Mat
chin
g
Valu
e M
atch
ing
Syntactic Matching 2
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
Approach (4)
User Profile Data
Ontology Mapping
Online Profile Resolution
Linguistic Analysis
Semantic Search
Extension
Ontology-enhanced Attribute
Weighting
A
B
D
Matching AttributesC1 3 42
Dire
ct S
trin
g M
atch
ing
Indi
rect
Str
ing
Mat
chin
g
Valu
e M
atch
ing
Syntactic Matching 2
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
Approach (4)
User Profile Data
Ontology Mapping
Online Profile Resolution
Linguistic Analysis
Semantic Search
Extension
Ontology-enhanced Attribute
Weighting
A
B
D
Matching AttributesC1 3 42
Dire
ct S
trin
g M
atch
ing
Indi
rect
Str
ing
Mat
chin
g
Valu
e M
atch
ing
Syntactic Matching 2
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
Approach (4)
User Profile Data
Ontology Mapping
Online Profile Resolution
Linguistic Analysis
Semantic Search
Extension
Ontology-enhanced Attribute
Weighting
A
B
D
Matching AttributesC1 3 42
Dire
ct S
trin
g M
atch
ing
Indi
rect
Str
ing
Mat
chin
g
Valu
e M
atch
ing
Syntactic Matching 2
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
Approach (4)
User Profile Data
Ontology Mapping
Online Profile Resolution
Linguistic Analysis
Semantic Search
Extension
Ontology-enhanced Attribute
Weighting
A
B
D
Matching AttributesC1 3 42
Dire
ct S
trin
g M
atch
ing
Indi
rect
Str
ing
Mat
chin
g
Valu
e M
atch
ing
Syntactic Matching 2
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
Approach (5)
User Profile Data
Ontology Mapping
Online Profile Resolution
Linguistic Analysis
Semantic Search
Extension
Ontology-enhanced Attribute
Weighting
A
B
D
Matching AttributesC1 3 42
Dire
ct S
trin
g M
atch
ing
Indi
rect
Str
ing
Mat
chin
g
Valu
e M
atch
ing
Syntactic Matching 2
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
Implementation
Transformation
Linguistic Analysis
Large KBGazetteer Lookup
PIM
ANNIE Information
Extraction System
Organisation
“DERI, Lower Dangan, Galway, Ireland”
Street City Country
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
Final Objective
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
Summary
Objectiveso Determination of
semantic equivalence between contacts described in online profiles
o Aggregated profile data is lifted onto a unique PIM representation and integrated in a super profile
Future Worko Integration of further
online accountso Semantic extension to
the syntactic-based profile attribute matching
o Definition of a metrico Analysis of online posts
from multiple accountso Evaluation of artefact
Thank you for your attention