摘要
近年来,社区问答服务系统(CQA)越来越受到人们的欢迎,但随着提问规模的膨胀,获得回答的问题比重逐步降低,且答案质量无法得到保障.为了提高问答系统中问题被解答的概率,并提升答案可信度,文中提出了基于社交关系相似度的社交问答系统(SQA),主动寻找与提问者社交关系紧密且能够回答问题的用户,并提出了针对提问者与最佳回答者的推荐方法.实验结果表明,在主观性强或实时性强等问题集上,文中方法能更快地得到让提问者满意的答案.
In recent years, community question answering (CQA) system has become more and more popular. However, with the expansion of question scale, the proportion of questions that have been answered reduces gradually, and the quality of answers cannot be guaranteed. In order to increase the answering probability of the questions in questioning and answering (Q&A) system and enhance the credibility of answers, a social question answering system on the basis of social relationship similarity is proposed, and a method is presented to find suitable respondents who are willing to answer and are familiar with related fields. Moreover, a recommendation method of the best answer and the best respondents is given. Experimental results show that, on subjectivity or real-time problem sets, the proposed method helps obtain satisfactory answers faster in comparison with traditional Q&A systems.
出处
《华南理工大学学报(自然科学版)》
EI
CAS
CSCD
北大核心
2015年第1期132-139,共8页
Journal of South China University of Technology(Natural Science Edition)
基金
国家自然科学基金资助项目(61300137)
广东省自然科学基金资助项目(S2013010013836)
华南理工大学中央高校基本科研业务费专项资金资助项目(2012ZM0077)~~
关键词
问答系统
社交关系相似度
社交网络
question answering system
social relationship similarity
social networking