Prediction of Users' Response Time in Q&A Communities

Social media and online Question and Answer (Q&A) communities in particular have become a successful solution for finding answers on diverse topics. However, not all questions are answered by these communities. Also, many questions are not answered quickly enough. In this paper, we propose a framework for predicting users' response time. The framework uses a diverse set of features including information on users, the content they generate while communicating, question tags, spatial and temporal features. Then these features are used as input for training predictive models by various machine learning algorithms. As a case study, three diverse Q&A communities from Stack Exchange are selected to test the framework. We demonstrate that Deep Belief Networks outperform Logistic Regression (LR), k-nearest neighbors (k-NN), and Decision Trees (DT) in the accuracy of the prediction across the three diverse Q&A communities.