User Feedback for Improving Question Categorization in Web-Based Question Answering Systems

Question categorization, which automatically suggests a few categories to host a user's question, is a useful technique in Web-based question answering systems. In this paper, we propose a question categorization method which makes use of user feedback to the system's automatic suggestions to improve question categorization. We initialize the categorization model by training a set of accumulated questions. When a user asks a question, the system automatically suggests a few categories for the question using the current categorization model. The user can then select one of these suggestions or another category and such feedback information is used to revise the categorization model. The revised model is used to categorize new questions. Experimental results show that our method is effective to take the advantages of both positive and negative feedback to improve the precision of question categorization but finish the revision of the categorization model in real time.