Dr Matthew Rowe

Lecturer

Research Overview

My core research interest is in the area of Social Computing where I examine how users, communities, and networks evolve on social media. I am also interested in data-driven approaches towards informing digital rights and accountability. In particular, my research examines the following topics:

  • Churn prediction (from online services, applications, and communities) using machine learning techniques.
  • Recommender systems with collaborative filtering - with an emphasis on latent-factor models.
  • Information diffusion models (e.g. general threshold, multivariate cascades).
  • Large-scale data mining using parallel-processing techniques implemented over distributed hardware.

Selected Publications Show all 65 publications

Mining user lifecycles from online community platforms and their application to churn prediction
Rowe, M. 12/2013
Conference paper

Who will follow whom?: Exploiting semantics for link prediction in attention-information networks
Rowe, M., Stankovic, M., Alani, H. 11/11/2012
Conference paper

Community analysis through semantic rules and role composition derivation
Rowe, M., Fernandez, M., Angeletou, S., Alani, H. 2012 In: Journal of Web Semantics. 18, 1, p. 31–47. 17 p.
Journal article

What catches your attention?: an empirical study of attention patterns in community forums
Wagner, C., Rowe, M., Strohmaier, M., Alani, H. 4/06/2012
Conference paper

What makes communities tick?: community health analysis using role compositions
Rowe, M., Alani, H. 1/09/2012 In: Privacy, Security, Risk and Trust (PASSAT), 2012 International Conference on and 2012 International Confernece on Social Computing (SocialCom). IEEE p. 267-276. 10 p.
Paper