Question Recommendation and Answer Extraction in Question Answering Community

Abstract

Every day, there are a large number of new questions produce in question answering community, how to find the answer user for the question and sort candidate answers is the research content of this paper. First of all ,we use statistical language model to model for user interest, make full use of the abundant personalized information in question answering community to find out user interest distribution, and obtain the user list of question recommendation by introducing the query likelihood language model to calculate the degree of user interest to the new question. Secondly, we calculate the matching degree of question and candidate answers through fusing the feature of word form, word order, distance and semantic. The candidate answers of question will be sorted automatically, making it easier for users to choose the best answer. Experiments are performed on data sets extracted from the Baidu know, experimental results show that the method proposed in this paper has better performance.\