Topic Detection in Online Discussion Using Non-negative Matrix Factorization

While topic detection based on document corpus has gained significant advances in recent years, the analysis of online discussion is often limited by its terseness and conversational style of writing. Using non-negative matrix factorization, user participation models can be developed to help us gain insights on the latent base topics of online discussions. Furthermore, the factorizations allows an automatic discovery of leaders and sub-communities in the online forum. Results on topic detection in online forum as well as the clustering results of several online forums are given.