首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于并行算法的话题检测及情感分析的研究
引用本文:申华,蒋廷鹏,汪若蓝.基于并行算法的话题检测及情感分析的研究[J].鞍山师范学院学报,2014(6):56-60.
作者姓名:申华  蒋廷鹏  汪若蓝
作者单位:1. 鞍山师范学院 数学与信息科学学院,辽宁 鞍山,114007
2. 大连理工大学 软件学院,辽宁 大连,116024
摘    要:在大数据时代,社交网络数据日益剧增,有效分析社交网络信息将对政府的合理决策起到促进作用.在海量的社交网络信息中,用户行为的数据分析是近些年来研究的热点问题.利用社交网络,用户可以关注当前的热点话题,并进行评论或者发布其他信息.这一系列行为反映出用户对于不同话题的偏好性和情感的倾向性,进而提供出有价值的潜在信息.本文设计了一种并行算法,实现了在Twitter和新浪微博数据上识别热点话题,并对用户情感进行分析.实验结果表明,该方法可以有效地监控热点话题及用户情感,具有重要的现实意义.

关 键 词:社交网络  话题检测  情感分析  并行算法

Research of Hot Topic Detection and User Sentiment Analysis Based on Parallel Algorithms
SHEN Hua,JIANG Tingpeng,WANG Ruolan.Research of Hot Topic Detection and User Sentiment Analysis Based on Parallel Algorithms[J].Journal of Anshan Teachers College,2014(6):56-60.
Authors:SHEN Hua  JIANG Tingpeng  WANG Ruolan
Institution:SHEN Hua ,JIANG Tingpeng, WANG Ruolan (1. School of Mathematics and Information Science ,Anshan Normal University,Anshan Liaoning 114007, China; 2. School of Software ,Dalian University of Technology,Dalian Liaoning 116024, China)
Abstract:In big data era,the number of users of online social networks improves dramatically. With the help of these users' information,it can support governments to make beneficial decision. In social networks analysis,analyzing user behavior is a hot topic in recent research fields. Users can generate content,follow hot topics and provide their own opinion on these topics. In order to analyze users' preference and attitude on prevalent topics,we proposed a parallel algorithm to detect users' behavior and collect hot topics. Experimental results show that the proposed method can detect hot topics and analyze users' sentiment effectively.
Keywords:Social networks  Topic detection  Sentiment analysis  Parallel algorithm
本文献已被 CNKI 维普 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号