Existing Research and Future Research Agenda
Upcoming SlideShare
Loading in...5
×
 

Existing Research and Future Research Agenda

on

  • 1,149 views

 

Statistics

Views

Total Views
1,149
Views on SlideShare
980
Embed Views
169

Actions

Likes
0
Downloads
3
Comments
0

2 Embeds 169

http://www.matthew-rowe.com 158
http://matthew-rowe.com 11

Accessibility

Categories

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.

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

Existing Research and Future Research Agenda Existing Research and Future Research Agenda Presentation Transcript

  • EXISTING RESEARCHANDFUTURE RESEARCHAGENDADR MATTHEW ROWERESEARCH ASSOCIATEKNOWLEDGE MEDIA INSTITUTEhttp://www.matthew-rowe.comm.c.rowe@open.ac.uk
  • The Big Picture 1 2006-2010: Ph.D.: ‘Disambiguating Identity Web References using Social   Data’. The University of Sheffield 2010-2012: Research Associate at the Knowledge Media Institute, The Open   University Ph.D. Research Associate Future Work 2006-2010 2010-2012 Digital Identity Digital Identity Identity Diffusion Lifecycles User Behaviour TimeDr Matthew Rowe - Existing Research and Future Research Agenda
  • Digital Identity Digital Identity Digital Identity Identity Diffusion Lifecycles User Behaviour 2   Personal information is spread across the Web: (a) identity theft, (b) lateral surveillance  Identity theft costs the UK government £1.2 billion per annum (Get Safe Online, 2010)   Manually tracking web citations is time-consuming and repetitive  57% of web users perform ‘vanity’ searches (Pew Internet Report, 2010) How can identity web references be disambiguated automatically? Seed data leveraged from Social Web Systems   Information extracted from candidate citations and semantic model built   Devised three disambiguation methods that combine data mining with semantics  Dr Matthew Rowe - Existing Research and Future Research Agenda
  • Digital Identity Digital Identity Digital Identity Identity Diffusion Lifecycles User Behaviour 3   Seed Data generation:  Large overlap between offline social networks and online social networks  Exporting semantic social graphs from disparate social web systems (Twitter, Facebook)  Machine-readable user profile and social network information  Interlinking social graphs from disparate social web systems   Disambiguation methods  Rule-based:infer relations between social data and web resources  Graph-based: random walks over a graph space and clustering  Semi-supervised machine learning: classify web citations and learn from classifications   Findings:  Socialdata provides necessary seed data to disambiguate web citations  Achieve best performance using semi-supervised methods, outperforming several baselines (unsupervised methods) Rowe and Ciravegna. Disambiguating Identity Web References using Web 2.0 Data and   Semantics. Journal of Web Semantics. 2010  http://www.matthew-rowe.com/?q=thesisDr Matthew Rowe - Existing Research and Future Research Agenda
  • Digital Identity User Behaviour Digital Identity Identity Diffusion Lifecycles User Behaviour 4   Attention Patterns on Social Web Systems   How is user behaviour associated with heightened attention?   Developed a machine learning approach to:   Identify seed posts   Predict discussion lengths   User Modelling: social network properties, topical focus, community affinity   Patterns associated with increased attention:  Twittter: greater broadcast spectrum  Boards.ie: greater community affinity, focussed users  SAP: less community messages, popular users (frequently provide answers) Rowe et al. Anticipating Discussion Activity on Community Forums. 3rd IEEE International Conference on Social   Computing, Boston, USA. 2011 Rowe et al. Predicting Discussions on the Social Semantic Web. Extended Semantic Web Conference, Heraklion,   Crete. 2011 Wagner et al. What catches your attention? An empirical study of attention patterns in community forums.   International Conference on Weblogs and Social Media, Dublin, Ireland. 2012Dr Matthew Rowe - Existing Research and Future Research Agenda
  • Digital Identity User Behaviour Digital Identity Identity Diffusion Lifecycles User Behaviour 5 Behaviour Analysis in Online Communities    How can the contextual notion of behaviour be captured?  What is the relation between community behaviour and health?  Modelled user behaviour along six dimensions:  Focus Dispersion, Initiation, Contribution, Popularity, Engagement, Content Quality  Modelled behaviour using semantic web technologies:  Behaviour Ontology – capturing contextual notion of behaviour  Inference rules – identifying the role of a given user  Mined roles, and associated behaviour, on a given platform  Correlated the time-series role composition of communities and with health indicators  Found certain roles to be associated with decreases in community health  E.g. Expert Initiators linked to community churn  Roweet al. Community Analysis through Semantic Rules and Role Composition Derivation. Journal of Web Semantics (in press). 2012Dr Matthew Rowe - Existing Research and Future Research Agenda
  • Digital Identity User Behaviour Digital Identity Identity Diffusion Lifecycles User Behaviour 6   Churn  Churn is the loss of users from a service (telecommunications/social network, online community)  Goal: predict churners and identify churn patterns  Using social network features (i.e. centrality) provided accurate information for churn detection  Found:  Differing churn patterns between communities  Central users churn in some communities, while peripheral users churn in others  Currently exploring: Churn diffusion and topological effects  Karnstedtet al. The Effect of User Features on Churn in Social Networks. ACM Web Science Conference 2011, Koblenz, Germany. 2011Dr Matthew Rowe - Existing Research and Future Research Agenda
  • The Big Picture - Revisit 7 Ph.D. Research Associate Future Work 2006-2010 2010-2012 Digital Identity Digital Identity Identity Diffusion Lifecycles User Behaviour TimeDr Matthew Rowe - Existing Research and Future Research Agenda
  • Digital Identity Identity Lifecycles Digital Identity Identity Diffusion Lifecycles User Behaviour 8  Identity is developed and shaped over time through developmental stages (Eriksson, 1959)  Ego-identity is the ideal that people pursue, while identity is a person’s present state (Bosma et al., 1994)  How are digital identities shaped online? Do the stages resonate with Eirksson’s theories?  What development stages do they go through? Is there a common life cycle across systems?  In role analysis there are common transitions from one role to another What are the motivations behind digital identity formation and amendments?    Self-efficacy  Self-affirmation Understanding identity lifecycles leads to:    Better recommendations (followees, products, content)  Tracking of disseminated personal information  Identifying users susceptible to ‘stealing reality’ attacks (Altshuler et al., 2011)Dr Matthew Rowe - Existing Research and Future Research Agenda
  • Digital Identity Identity Diffusion Digital Identity Identity Diffusion Lifecycles User Behaviour 9 Identity Diffusion is the propagation of identity attributes through social systems    I.e. the adoption of defining characteristics from neighbours What network effects are associated with identity diffusion?    Smallcore of central users found to be influential in protest recruitment (Gonzalez-Bailon et al., 2011)  Core web sites found to influence the spread of memes (Gomez-Rodriguez et al., 2012) What is the role of passive/active networks on identity formation?    Behaviour adoption is maintained through social reinforcement (Centola, 2010) Local-level influence (i.e. homophily, inequity, balancing)    Weak-tied individuals in ego-networks influence adoption (Garg et al., 2011)  Inverse correlation between node influence and degree (Katona et al., 2011) What effects do community actions have on web presence and subscriber churn?    Onlinecommunity churn (Karnstedt et al., 2010), (Zhang et al., 2010), (Kawale et al., 2010)  Recently studied in the context of ego-networks (Quercia et al., 2012), (Kwak et al., 2011) Understanding and modelling identity diffusion leads to:    Identification of links between behaviour and churn from online systems  Enable understanding of reductions in web presence (Online marketing, brand promotion)Dr Matthew Rowe - Existing Research and Future Research Agenda
  • The Big Picture - Recap 10 Ph.D. Research Associate Future Work 2006-2010 2010-2012 Digital Identity Digital Identity Identity Diffusion Lifecycles User Behaviour TimeDr Matthew Rowe - Existing Research and Future Research Agenda
  • 11 Questions? http://www.matthew-rowe.com m.c.rowe@open.ac.ukDr Matthew Rowe - Existing Research and Future Research Agenda