提出一种基于主题情感句的汉语评论文倾向性分析方法.根据评论文的特点,采用一种基于n元词语匹配的方法识别主题,通过对比与主题的语义相似度和进行主客观分类抽取出候选主题情感句,计算其中相似度最高的若干个句子的情感倾向,将其平均值作为评论文的整体倾向.基于主题情感句的评论文倾向性分析方法避免了进行篇章结构分析,排除了与主题无关的主客观信息,实验结果表明,该方法准确率较高,切实可行.%This paper presented an approach to recognizing sentiment polarity in Chinese reviews based on topic sentiment sentences.Considering the features of Chinese reviews, it identified the topic of a review using an n-gram matching approach.To extract topic sentiment sentences, computed the semantic similarity of a candidate sentence and the ascertained topic and meanwhile determine whether the sentence was subjective.Selected a certain number of these sentences as representatives according to their semantic similarity value with relation to the topic.Calculated the average value of the representative topic sentiment sentences and regarded as the sentiment polarity of a review.Experiment result shows that the proposed method is feasible and can achieve relatively high precision.
展开▼