Classifying User Messages For Managing Web Forum Data.
Sumit Bhatia, Prakhar Biyani, Prasenjit Mitra · International Workshop on the Web and Databases · 2012
Online discussion forums have become a popular medium for users to discuss with and seek information from other users having similar interests. A typical discussion thread consists of a sequence of posts posted by multiple users. All the posts in a thread are not equally useful and serve a different purpose providing different types of information (some posts contain questions, some answers, etc.). Identifying the purpose and nature of each post in a discussion thread is an interesting research problem as it can help in improving information extraction and intelligent assistance techniques [9]. We study the problem of classifying a given post as per its purpose in the discussion thread. We employ features based on the post’s content, structure of the thread, behavior of the participating users and sentiment analysis of post’s content. We achieve decent classification performance and also analyze the relative importance of different features used for the post classification task.