计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (27): 147-151.

• 数据库、信号与信息处理 • 上一篇    下一篇

情感词汇Ontology驱动的话题倾向性计算

王晓东,刘 倩,张 征   

  1. 河南师范大学 计算机与信息技术学院,河南 新乡 453007

  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-09-21 发布日期:2011-09-21

Topic semantic orientation compute based on sentiment words Ontology

WANG Xiaodong,LIU Qian,ZHANG Zheng   

  1. Department of Computer Science,Henan Normal University,Xinxiang,Henan 453007,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-09-21 Published:2011-09-21

摘要: 针对“未然态”的舆情信息,挖掘网络热点、焦点及敏感话题,把握舆情动态,提高处置与监管网络突发事件能力等,是舆情分析的重要研究内容。对基于情感词汇Ontology的话题倾向性进行了研究。通过计算与情感词汇Ontology中情感词汇的语义相似度、统计话题语料中情感特征词汇的词频,计算语料中情感特征词汇的倾向性权重;根据情感特征词汇的倾向性权重计算话题倾向性强度和整体倾向性。最后在情感词汇Ontology指导下对话题中每篇语料的情感分类和倾向性强度进行规范化细粒度标注。

关键词: 舆情, 话题倾向性, 情感词汇Ontology

Abstract: In allusion to the unlighted public opinion information,the important aspects of public opinion analysis are as follows:network hot spots,focus and sensitive topic mining,public opinion trends control,the ability to handle and monitor the network emergency improvement and so on.Topic semantic orientation compute based on sentiment words ontology is studied.The orientation weights of the words are calculated by calculating the semantic similarity of the words in sentiment words ontology and counting the sentiment words frequencies in the topic corpus.Then the topic orientation extent and the overall orientation can be calculated according to the orientation weights of the words.Finally,the sentiment classification and orientation extent of each corpus in the topic is tagged by the fine-grained standard based on sentiment words ontology.

Key words: public opinion, topic orientation, sentiment words Ontology