针对Web 2.0时代大量主观性文本的出现,消费者在线评论描述了消费者关于某一产品或服务的观点或经历.本文基于模糊理论讨论了在线评论中的情感挖掘问题.以消费者心理行为学理论为基础,根据在线评论的自然语言模糊本质属性,建立了消费者心理模糊库群,包括特征、感知、情绪、评价等4个模糊库;结合评论语句的句法分析,给出了消费者态度情感的模糊计算算法(FSCA-OR);并依据消费者的决策过程,进行了推理规则库的构建;最后通过实验验证了所提方法的有效性.%In accordance with the abundant emergence of subjective texts in the Web 2. 0 eras, consumer online reviews descrihe consumer's concerns and their experience with products or services. This paper considers the sentiment mining problem of online reviews based on the fuzzy theory. Given fuzzy attribute nature of consumer attitude elements reflected by the online reviews, we have estahlished fuzzy group bases derived from consumer psychology and behavior.Four fuzzy bases, including features, sense, mood and evaluation, are estahlished. A fuzzy sentiment computing algorithm FSCA-OR is developed, and a fuzzy rule base is also huilt based on consumer decision-making process. Finally it shows by means of an experiment that the proposed approach is very well suited as an analysis tool for the online reviews sentiment mining problem.
展开▼
