Determine the Polarity of Domain-specific Sentiment Words with Usage of Semantic Pattern of Sentences

摘要：

　　Text sentiment analysis is a new branch of computational linguistics which is widely concerned.In this paper,we present an approach to determine polarity of sentiment word based on context of sentence.We first change the context of sentence to semantic pattern vector,calculate the between different sentences,then compare sentences context indirectly by comparing similarity of their pattern vector,next we annotate polarity of sentiment word according to comparing result.Experiment shows that when the context of two sentences have high similarity,it is likely to have high precision in recognizing polarity of sentiment word.Our study shows its feasible to use semantic pattern vector in representing context and judging polarity of sentiment words.

关键词： Sentiment word Polarity Semantic Pattern Context

作者: YANG Li-gong DENG Bo

作者单位: Department of Computer Science and Technology Beijing Institute of Technology Beijing,China

会议类型: 国际会议

会议名称: 2013 2nd International Conference on Computer Science and Electronics Engineering(ICCSEE2013)(2013年第二届计算机科学与电子工程国际会议)

会议地点: 杭州

会议语种:英文

页码: 2418-2421

在线出版日期: 2013-03-22（万方平台首次上网日期，不代表论文的发表时间）