Unsupervised learning by probabilistic latent semantic analysis
Machine Learning
Modern Information Retrieval
Learning Approaches for Detecting and Tracking News Events
IEEE Intelligent Systems
On the bursty evolution of blogspace
WWW '03 Proceedings of the 12th international conference on World Wide Web
The Journal of Machine Learning Research
Topic Detection from Blog Documents Using Users' Interests
MDM '06 Proceedings of the 7th International Conference on Mobile Data Management
Topic evolution and social interactions: how authors effect research
CIKM '06 Proceedings of the 15th ACM international conference on Information and knowledge management
Identifying opinion leaders in the blogosphere
Proceedings of the sixteenth ACM conference on Conference on information and knowledge management
Web video topic discovery and tracking via bipartite graph reinforcement model
Proceedings of the 17th international conference on World Wide Web
Topic initiator detection on the world wide web
Proceedings of the 19th international conference on World wide web
Tractable models for information diffusion in social networks
PKDD'06 Proceedings of the 10th European conference on Principle and Practice of Knowledge Discovery in Databases
Mining co-distribution patterns for large crime datasets
Expert Systems with Applications: An International Journal
Identifying valuable customers on social networking sites for profit maximization
Expert Systems with Applications: An International Journal
Expert Systems with Applications: An International Journal
Hi-index | 12.06 |
Over the last few years, online forums have gained massive popularity and have become one of the most influential web social media in our times. The forum document corpus can be seemed to be composed of various topics evolved over time, and every topics is reflected on a volume of keywords and social actors. In this paper, we attempt to study the interesting problem: for the evolving topics, were there any correlation between them? We propose a method for discovering the dependency relationship between the topics of documents in adjacent time stamps based on the knowledge of content semantic similarity and social interactions of authors and repliers. We introduce mutual information measure to estimate the correlation between the topics. Applied to the realistic forum data, we show how topics are related and which postings can be recommended to another as similar topics. We also show how the authors impact the topics and propose a new way for evaluating author impact.