Traditionally, text classifiers are built from labeled training examples. Labeling is usually done manually by human experts (or the users), which is a labor intensive and time co...
Much existing research on blogs focused on posts only, ignoring their comments. Our user study conducted on summarizing blog posts, however, showed that reading comments does chan...
Topic description is as important as topic detection. In this paper, we propose a novel method to describe Web topics with topic words. Under the assumption that representative wo...