Expert2Bólè: From Expert Finding to Bólè Search

Expert finding, aiming to answer the question: “Who are experts on topic X?”, is becoming one of the biggest challenges for information management. Much work has been conducted for expert finding. Methods based on language model, topic model, and random walk have been proposed. However, little work has studied why people want to find experts. In this work, we describe Expert2Bólè, a search tool that offers expert finding for various purposes. Specifically, we first employ the learning-to-rank techniques to learn a function for ranking experts. We further investigate a specific case of why people search experts, i.e. Bólè search, which tries to identify best supervisors in a given field. How to learn a good ranking function for Bólè search is a very challenging issue, since there would be very limited or even no supervised information which can be used to learn the ranking function. We propose a unified knowledge transfer approach which takes advantage of the expert finding knowledge to learn the ranking function for Bólè search. A prototype system has been developed for expert finding and Bólè search based on the proposed approach. Experiment results show the effectiveness of the proposed approach.