一种基于语料库的网络群体事件情感倾向分析模型  

A Model Based on Corpus for Analyzing Network Group Cognition of Emotional Tendency for Events

作　　者：白洁[1] 尹明辉 刘伟强 BAI Jie;YIN Minghui;LIU Weiqiang(The 54th Research Institute of CETC,Shijiazhuang 050081,China)

机构地区：[1]中国电子科技集团公司第五十四研究所,河北石家庄050081

出　　处：《计算机与网络》2021年第23期54-57,共4页Computer & Network

摘　　要：介绍了一种基于语料库的群体情感倾向度分析模型,该模型基于倾向性语料库中的极性词汇对集合中每一份素材文本进行分词,统计并计算素材文本中出现的极性词汇的强度值,得到整篇素材文本的倾向度,对集合中所有素材文本的倾向度进行统计并归一化,带入分段条件函数中进行倾向度判断,得到网络群体对该事件的情感倾向。通过对巴以冲突和中国空间站2个近期热点事件的对照测试,验证了模型的正确性。A model based on corpus for analyzing network group cognition of emotional tendency for events is introduced.The model divides each material text in the collection based on the polar words in the tendency corpus,counts and calculates the intensity value of the polar words appearing in the material text,and obtains the emotional tendency of the whole material text.Then,it counts and normalizes the degree of emotional tendency of all the material texts in the collection,brings it into the subsection conditional function to judge the emotional tendency,and obtains whether the network group’s emotional tendency to the event is positive,neutral or negative.The correctness of the model is verified by comparing two recent hot events:“Palestinian Israeli Conflict of 2021”and“China Space Station”.

关 键 词：极性词汇 语料库 情感倾向度 向量分析 

分 类 号：TP311.5[自动化与计算机技术—计算机软件与理论]