上海交通大学学报(英文版) ›› 2015, Vol. 20 ›› Issue (1): 32-37.doi: 10.1007/s12204-015-1584-0

• • 上一篇    下一篇

Generating Domain-Specific Affective Ontology from Chinese Reviews for Sentiment Analysis

LIU Li-zhen (刘丽珍), LIU Hao (刘昊), WANG Han-shi* (王函石),SONG Wei (宋巍), ZHAO Xin-lei (赵新蕾)   

  1. (College of Information Engineering, Capital Normal University, Beijing 100048, China)
  • 出版日期:2015-02-28 发布日期:2015-03-10
  • 通讯作者: WANG Han-shi (王函石) E-mail:wanghanshicnu@gmail.com

Generating Domain-Specific Affective Ontology from Chinese Reviews for Sentiment Analysis

LIU Li-zhen (刘丽珍), LIU Hao (刘昊), WANG Han-shi* (王函石),SONG Wei (宋巍), ZHAO Xin-lei (赵新蕾)   

  1. (College of Information Engineering, Capital Normal University, Beijing 100048, China)
  • Online:2015-02-28 Published:2015-03-10
  • Contact: WANG Han-shi (王函石) E-mail:wanghanshicnu@gmail.com

摘要: Considering the diversities and ambiguities of opinion expressions in Chinese online product reviews, normal sentiment analysis technologies have exposed their inadequateness in both classification accuracy and identifying effectiveness. We propose a novel approach which can easily identify product features and corresponding opinions by building a domain-specific affective ontology and thus mapping comment sentences to the objects defined in the affective ontology. Ontology is created automatically by processing the online reviews; both product features and affective words are presented as nodes which are connected to each other by their semantic relationship. Furthermore, in order to increase the accuracy, we introduce a dynamic polarity detection technique for affective words whose sentimental tendencies are dependent on particular contexts. The experimental results clearly demonstrate the performance improvement of our approach compared with others in real world online product reviews for classification tests.

关键词: affective ontology, sentimentanalysis, product features, Chinese reviews

Abstract: Considering the diversities and ambiguities of opinion expressions in Chinese online product reviews, normal sentiment analysis technologies have exposed their inadequateness in both classification accuracy and identifying effectiveness. We propose a novel approach which can easily identify product features and corresponding opinions by building a domain-specific affective ontology and thus mapping comment sentences to the objects defined in the affective ontology. Ontology is created automatically by processing the online reviews; both product features and affective words are presented as nodes which are connected to each other by their semantic relationship. Furthermore, in order to increase the accuracy, we introduce a dynamic polarity detection technique for affective words whose sentimental tendencies are dependent on particular contexts. The experimental results clearly demonstrate the performance improvement of our approach compared with others in real world online product reviews for classification tests.

Key words: affective ontology, sentimentanalysis, product features, Chinese reviews

中图分类号: