期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2015
卷号：3
期号：3
DOI：10.15680/ijircce.2015.0303005
出版社：S&S Publications
摘要：Opinion mining or sentiment analysis extract specified information from a large amount of text orreviews given by the internet users. Opinion mining classifies the large text of opinions as positive (good), negative(bad) or neutral. According to the number of positive, negative and neutral reviews, the product or service will be rated.Sometimes an overall rating for a review cannot be helpful to identify various features of a product or service. Forexample, a camera may come with excellent battery life but poor image quality. Hence more sophisticated aspect levelopinion mining approaches have been proposed to extract information from online reviews. In this paper, we arediscussing various approaches used for opinion mining. They are frequency-based approach, relation-based approach,supervised learning and topic modelling
关键词：Aspect mining; opinion mining; supervised learning; text mining
