汉语句子语义极性分析和观点抽取方法的研究

Semantic polarity analysis and opinion mining on Chinese review sentences

利用自然语言处理技术,对中文网络评论语句进行语义极性分析和观点抽取。提出了计算词语上下文极性的算法,并且分析主题和修饰成分的匹配关系。最后与手工标注结果进行比较,通过实验证明了该算法的合理性和有效性。

By using natural language management technology, Chinese Web review sentences were semantic studied and opinion mined. A new algorithm for computing the contextual polarity of polar words was proposed, and a framework was introduced for topic identification and feature extraction. The framework provided an innovative solution for the association of extracted opinion to its specific topic. The experiment results show that the algorithm is both reasonable and effective compared with the results of manual annotation.