Forum Summarization Using Topic Models and Content-Metadata Sensitive Clustering

The advent of the Internet and improvements in data sharing and storage, have resulted in an explosion of textual data. But, complete assimilation of such massive amounts of data in its raw form is a daunting task. Automated text mining methods such as text summarization present the user with a condensed version of data containing only key information. This is especially useful in the case of online user forums that contain a large number of posts spread out across several threads. Document summarization methods have been extensively studied and several methods have been developed in the recent past. This paper aims at developing a new method for automatic summarization of online forums by using topic models and content/metadata sensitive clustering.