Sentiment Classification Using Genetic Algorithm and Conditional Random Fields

摘要：

Sentiment classification has attracted increasing interest from Natural Language Processing. This paper explores the genetic algorithm to extract the best feature collections from the semantic features of emotional collections. Conditional Random Fields (CRFs) is employed to model the emotional tendency of web pages which are divided into different types of comments, such as positive comments, negative comments and objective comments. Experimental results on both the product reviews and the 1998 Peoples Daily corpus show that the proposed algorithm works reasonable in the real calculation.

关键词： sentiment classification genetic algorithm conditional random fields

作者: Jian Zhu Hanshi Wang JinTao Mao

作者单位: School of Computer ScienceBeijing Institute of TechnologyBeijing, China School of Computer ScienceBeijing Institute of TechnologyBeijing,China School of Computer Science Beijing Institute of Technology Beijing,China

会议类型: 国际会议

会议名称: 2010 2nd IEEE International Conference on Information Management and Engineering(2010年IEEE第二届信息管理与工程国际会议 IEEE ICIME 2010)

会议地点: 成都

会议语种:英文

页码: 1-4

在线出版日期: 2010-04-16（万方平台首次上网日期，不代表论文的发表时间）