Towards modeling question popularity in community question answering

Community question answering (QA) has become increasingly popular and received a great variety of questions every day. Among them, some questions are very attractive and popular to many users, while some other questions are very tedious and unattractive. In this paper, we aim to identify popular questions in the community QA through modeling question popularity. Three popularity-related features of questions are defined to build the popularity model: (a) potential hits, which reflect how many users are attracted by a question at their first glance; (b) popular terms, from which users find a question attractive; and (c) tedious unpopular terms. The notable characteristic of the proposed framework is extensibility and more features can be incorporated. A large-scale question dataset from a practical community QA website was used to train and test the model. Meanwhile, two well-known classifiers, k-nearest neighbors and support vector machines, were implemented for comparison. Our approach is well validated by the experimental results with much higher prediction accuracy than the baseline methods.