摘要
[目的/意义]面对海量的微博数据,及时准确地检测出微博突发事件,对于网络舆情检测有着重要的意义。[方法/过程]在对微博突发事件传播规律的研究分析中,发现事件相关微博文档的发布地域覆盖范围会随事件演变,出现从小开始逐渐扩大,再到出现极值,最后逐渐缩小的规律,根据该规律提出一种基于突发词地域分析的微博突发事件检测方法。该方法从突发词的地域属性和情感属性两个维度去识别微博突发事件,首先通过情感计算过滤非负值文档;然后根据特征词的地域扩散程度对剩余文档进行突发词检测;最后使用新突发事件检测方法,对突发词集进行聚类,从而发现微博突发事件。[结果/结论]实验结果表明该微博突发事件检测方法与两个对比文献相比,正确率、召回率和F均值均有明显提升。
[ Purpose/Significance] Facing the massive micro-blog data, to detect the micro-blog bursty events timely and accurately is of great significance to the network public opinion monitoring. [ Methotl/Proeess] A kind of rule was found by the research and analysis of propagation rule of the microblog bursty events, which was that the regional coverage of event related microblog documents began to gradually expand, then to the extreme and finally gradually narrowed along with the evolution of events, according to this rule, a method of microblog bursty events detection based on burst words regional analysis was proposed in this paper. The two dimensions which were regional property and sentiment property of burst words were used to identify the microblog bursty events. Firstly, the positive of documents were filtered by emotional calculating. Then, burst words from the remaining documents were detected according to the degree of regional diffusion of the feature words. Finally, a new but＇sty event detection method was introduced to cluster the burst word set for finding the microblog bursty events. [ Result/Conclusion] The experimental results show that comparing with two comparative literature, our method of microblog bursty events detection in the precision, recall and F average has improved obviously.
出处
《情报杂志》
CSSCI
北大核心
2017年第3期98-103,97,共7页
Journal of Intelligence
基金
广西高等学校科学研究项目"Web文本情感分析并行算法研究"(编号:KY2015YB008)研究成果之一
广西大学科研基金项目"网络舆情热点发现并行算法研究"(编号:XJZ130355)研究成果之一
关键词
突发事件检测
突发词
地域分析
情感过滤
微博
bursty events detection burst word regional analysis sentiment filter microblog
