Back to Research Areas
  
Research
 

SIS Research Area - Data Management & Analytics

Research Theme
 Social Network Mining

Central Concerns and Questions

We investigate the mining of network structures, network evolution, and users and objects' behavior patterns from user-generated data so as to personalise applications making them more user-friendly, and to moderate user interactions by introducing novel applications that detect undesired behaviors. We also study the problem of predicting inter-user trust among users for the purpose of recommendation and search.

Emerging Ideas and Initiatives

We have so far conducted social network mining research on online rating data, Wikipedia and email data. For online rating data, we have developed models for determining leniency and bias of raters when they rate items, and relating them to the items' quality. We have also developed models for measuring user and object dependency on a pair of rating criteria so as explain some rating data patterns. We also apply social network mining to Wikipedia data to find interesting articles including the ones with controversial content. In trust prediction, we are investigating rating interaction data features that allow us to determine trust between users.

Selected Publications

[1] Hady Wirawan Lauw, Ee-Peng Lim, Ke Wang. On Mining Rating Dependencies in Online Collaborative Rating Networks. Pacific Asia Conference on Knowledge Discovery and Data Mining (PAKDD2009), Bangkok, May 2009.

[2] Meiqun Hu, Ee-Peng Lim, Ramayya Krishnan. Predicting Outcome for Collaborative Featured Article Nomination in Wikipedia, 3rd International AAAI Conference on Weblogs and Social Media (ICWSM2009), San Jose, May 2009.

[3] Maggy Anastasia Suryanto, Ee Peng Lim, Aixin Sun, Roger Chiang. Quality-Aware Collaborative Question Answering:Methods and Evaluation, ACM International Conference on Web Search and Data Mining (WSDM 2009), Barcelona, Spain, February 2009.

[4] Hady Wirawan Lauw, Ee-Peng Lim, Ke Wang. Bias and Controversy in Evaluation Systems. IEEE Transactions on Knowledge Data Engineering 20(11): 1490-1504, 2008.

[5] M.-T. Le, H.-V. Dang, E.-P. Lim, A. Datta. WikiNetViz: Visualizing Friends and Adversaries in Implicit Social Networks. IEEE International Conference on Intelligence and Security Informatics (ISI2008), 2008.

[6] B.-Q. Vuong, E.-P. Lim, A. Sun, M.-T. Le, H.W. Lauw, K. Chang. On Ranking Controversies in Wikipedia: Models and Evaluation. 1st ACM International Conference on Web Search and Data Mining (WSDM2008), 2008.

Projects, Presentations and Posters

  2. Keynote talk on "Collective Intelligence in Web2.0" at the Infovision 2009 - The Knowledge Summit, Bangalore , January 22-23, 2009.
  3. Ee-Peng Lim, Behavior Mining in Wikipedia, keynote speaker at The Fourth Annual Conference on Collaboration Technologies, Wakayama, Japan, August 30-31, 2008.
  4. Ee-Peng Lim, On Ranking Controversies in Wikipedia: Models and Evaluation, Presentation at The First ACM International Conference on Web Search and Data Mining (WSDM2008) Stanford, February 2008.

External Collaborations and Industry Linkages

  1. Ke Wang, Simon Fraser University
  2. Ramayya Krishnan, Carnegie Mellon University
  3. Bing Liu, University of Illinois at Chicago
  4. San-Yih Hwang, National Sun Yat-Sen University
  5. Aixin Sun, Nanyang Technological University
  6. Anwitaman Datta, Nanyang Technological University
  7. Hady Wirawan Lauw, Microsoft Search Lab
  8. Teow Loo Nin, DSO National Laboratories


Last updated on 9 November, 2009 by School of Information Systems.