Incorporating social information to perform diverse replier recommendation in question and answer communities

Social information is contextual information that has made significant contributions to intelligent information systems. However, social information has not been fully used, especially in question and answer (Q&A) systems. This study describes a contextual recommendation method in which diverse repliers are recommended for new questions using incorporated social information in Q&A communities. We have mined multiple kinds of social information by analysing social behaviours and relations found in a Q&A community and proposed an algorithm to incorporate different social information in various social contexts to perform diverse repliers' recommendations. Recommendation diversity and social contexts have been considered and the properly used social information has been emphasized in this study. We conducted experiments using a dataset collected from the Stack Overflow website. The results demonstrate that different social information makes different contributions in promoting question answering, and incorporating social information properly could improve recommendation diversity and performance, which would then result in the promotion of satisfactory question solving.