基于产品特征聚类的产品评论信息挖掘研究
首发时间:2013-08-09
摘要:产品评论中的产品特征及情感倾向是一种反映产品价值的重要信息,针对现有的中文产品评论信息挖掘存在的不足,提出了一种基于词汇共现性的产品特征聚类技术与细粒度情感分析技术。在产品评论中,同类的产品属性会有着多种多样的表述方式,文章把产品评论中的产品特征进行归类,且与以往基于句子的整体情感分析不同,提出了针对产品特征的更细粒度情感分析技术,并且对没有相应情感倾向的属性词做出合理处理。
关键词: 计算机应用技术 产品特征归类 相邻共现 细粒度情感分析 非极性观点词
For information in English, please click here
Information Mining of Product Comment Based on Product Feature Cluster
Abstract:Product features and emotional tendencies in product reviews reflect the value of things. We present a product feature cluster technology based on vocabulary co-occurrence and a fine-grained emotion analysis technology. In product comments, one feature may have various of means of expression, this paper classified features in product comments, presents a more fine-grained emotion analysis technology different from former emotion analysis that based on sentence. In addition, reasonable processing method is presented for the features without corresponding emotion tendency.
Keywords: computer application technology cluster of product features co-occurrence fine-grained emotion analysis non-polar viewpoint
论文图表:
引用
No.****
同行评议
共计0人参与
勘误表
基于产品特征聚类的产品评论信息挖掘研究
评论
全部评论0/1000