摘要
[目的/意义]为解决社会化问答社区用户信息需求多样化和答案冗余过载问题,提出面向用户个性化需求的答案有用性排序方法,协助用户高效筛选和获取有用的答案知识。[方法/过程]首先通过文献调研和专家咨询法,从答案特征、回答者特征、答案的时效性3个维度构建答案有用性评价指标体系;然后,从语义层面融合用户个性化需求,设计融合加权灰色关联分析法和Word2vec的答案有用性排序方法,实现面向用户需求的答案排序。[结果/结论]通过实验结果的对比分析发现与基于"点赞数"和"回答时间"等传统的排序方法相比,笔者设计的答案有用性排序方法的用户满意度更高,更能够满足用户的个性化知识需求。
[Purpose/significance]In order to solve the diversified information needs of users and the problem of redundant and overloaded answers in the social Q&A community,this paper proposes an answer usefulness ranking method oriented to users'personalized needs,assists users to efficiently filter and obtain useful answer knowledge.[Method/process]First,through literature research and expert consultation,an answer usefulness evaluation index system was constructed from the three dimensions of answer characteristics,answerer characteristics and answer timeliness;Then,it integrated the user's personalized needs from the semantic level,designed an answer usefulness ranking method that combined WGRA and Word2vec,and realized the answer ranking oriented to user needs.[Result/conclusion]Through comparative analysis of experimental results,it is found that compared with traditional ranking methods based on"likes"and"answer time",the answer usefulness ranking method designed in this paper has higher user satisfaction and is more able to satisfy users'personalized knowledge demands.
作者
郭顺利
步辉
Guo Shunli;Bu Hui(School of Communication,Qufu Normal University,Rizhao 276800)
出处
《图书情报工作》
CSSCI
北大核心
2021年第23期126-135,共10页
Library and Information Service
基金
国家社会科学青年基金项目"基于认知计算的网络问答社区知识的深度聚合及精准服务研究"(项目编号:20CTQ028)研究成果之一。