Research On Experts Finding And Question Recommendation Mechanism Of User-Interactive Q&A Platform

In the field of information retrieval, compared with the search engine, which uses user typed keywords to retrieve data, the user-interactive Q&A platform adopts the natural language, which has richer semantics. Baidu Knows, Yahoo! Answers, Quora, and popular ZhiHu, these user-interactive Q&A platforms have become important channels for users to get information and share knowledge. However, with the development of the user-interactive Q&A platform, the number of users as well as Q&A data is increasing quickly. For any user, the question just submitted may soon be flooded by other new submitted ones. The consequence is that the user may take long time to get an answer. In addition, they may not get the answer to their satisfaction, and even contains a lot of spam.By researching on experts finding and question recommendation mechanism, the paper attempts to help questioners who wait passively to get answers in the shortest time. In the meantime, these answers will make them feel satisfied. The author analyzed and summarized the status and features of the user-interactive Q&A platform through statistical method. Then, the improved PageRank algorithm is proposed and applied to the experts finding in the Q&A community. Finally, based on the research of experts finding, the question recommendation architecture and recommendation process is designed for the user-interactive Q&A platform, by which the system can automatically recommend questions to appropriate users.The author uses Java code to implement proposed algorithms, and the experiment proves the validity and feasibility of the experts finding method proposed by this paper. In the meantime, a sample prototype system is developed to display the question recommendation process.