A Social Network-Based Approach to Expert Recommendation System

We present a hybrid method for an expert recommendation system that integrates the characteristics of content-based recommendation algorithms into a social network-based collaborative filtering system. Our method aims at improving the accuracy of the recommendation prediction by considering the social aspect of experts' behaviors. For this purpose, social communities of experts are first detected by applying social network analysis and using factors such as experience, background, knowledge level, and personal preferences of experts. Representative members of communities are then identified using a network centrality measure. Finally, a recommendation is made to relate an information item, for which a user is seeking for an expert, to the representatives of the most relevant community. Further from an expert's perspective, she/he has been suggested to work on relevant information items that fall under her/his expertise and interests.