PROJECT TITLE :

A Multi-objective Optimization Approach for Question Routing in Community Question Answering Sevices - 2017

ABSTRACT:

Community Question Answering (CQA) has increasingly become an important service for people asking questions and providing answers on-line, which allows individuals to help each different by sharing knowledge. Recently, with accumulation of users and contents, abundant concern has arisen over the potency and answer quality of CQA services. To handle this downside, question routing has been proposed which aims at routing new queries to acceptable answerers, who have each high chance and high ability to answer the queries. In this paper, we tend to formulate question routing as a multi-objective ranking problem, and present a multi-objective learning-to-rank approach for question routing (MLQR), that can simultaneously optimize the answering possibility and answer quality of routed users. In MLQR, realizing that questions are relatively short and sometimes hooked up with tags, we tend to 1st propose a tagword topic model (TTM) to derive topical representations of questions. Based on TTM, we have a tendency to then develop options for every question-user try, which are captured at both platform level and thread level. In particular, the platform-level features summarize the data of a user from his/her history posts within the CQA platform, while the thread-level options model the pairwise competitions of a user with others in his/her answered threads. Finally, we have a tendency to extend a state-of-the-art learning-to-rank algorithm for training a multi-objective ranking model. Intensive experimental results on real-world datasets show that our MLQR can outperform state-of-the-art methods in terms of both answering risk and answer quality.