Extracting Product Features from Chinese Customer Reviews

摘要：

E-commerce,or business done on the Internet hasbecome more and more popular.Meanwhilo thenumber of customer reviewts for products on theinternet grows capidly.For a popular product,thenumber of reviews can be in hundreds.As a result,theproblem of opinion mining has seen increasingattention over several years.In this paper,weproposed a statistical method to extract productfeatures from Chinese customer reviews.The method isbased on distribution of a candidate word in differentdomains and within the certain domain.It also takesinto account the unbalance size of different productreviews.Experimental results show that it achievesbetter performance than other methods.

关键词： opinion mining product feature extraction customer review

作者: Yu Zheng Liang Ye Geng-feng Wu Xin Li

作者单位: School of Computer Engineering and Science,Shanghai University School of Electromechanical Engineering and Automation,Shanghai University Shanghai200072,P.R.China

会议类型: 国际会议

会议名称: 2008 3rd International Conference on Intelligent System and Knowledge Engineering(第三届智能系统与知识工程国际会议)(ISKE 2008)

会议地点: 厦门

会议语种:英文

页码: 285-290

在线出版日期: 2008-11-17（万方平台首次上网日期，不代表论文的发表时间）