摘要
问答社区作为搜索引擎的补充,在人们生活中起到越来越重要的作用,但随着大量问答对的积累,部分答案不能及时得到其他用户的评价,使得提问者选择最佳答案的难度加大。文中在研究用户行为及其行为所产生的结果后,提出一种新的基于主题模型的候选答案排序方法。通过大规模的实验数据证明,相较于其他模型方法,取得了较好的效果。
As a supplement of search engine,community question and answering is playing a more and more important role. But with increasing numbers of questions and answers,part of the answers fail to get the evaluation of other user in time,which makes it difficult for askers to choose the best answer. Based on the study of the user behavior of and its effects this paper proposes a new topic model on the basis of user behaviors. Experiments with large sets of data show that the proposed method is superior to other models.
出处
《电子科技》
2016年第5期130-134,共5页
Electronic Science and Technology
关键词
问答社区
答案排序
主题模型
用户行为
community question and answering
answer ranking
topic model
user behavior
