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：2017
卷号：5
期号：5
页码：9430
DOI：10.15680/IJIRCCE.2017.0505124
出版社：S&S Publications
摘要：With the rapid expansion of e-commerce, more and more products are sold on the Web, and more andmore people are also buying products online. In order to enhance customer satisfaction and shopping experience, it hasbecome a common practice for online merchants to enable their customers to review or to express opinions on theproducts that they have purchased. As more common users becoming comfortable with the Web, an increasing numberof people are writing reviews. Some popular products can get hundreds of reviews at some large merchant sites.Furthermore, many reviews are long and have only a few sentences containing opinions on the product. This makes ithard for a potential customer to read them to make an informed decision on whether to purchase the product. Here weaim to mine and to summarize all the customer reviews about products. In this work we analyse the sentimentsassociated with reviews for particular product and give result as positive, negative or neutral for that particular product.The user can also add his/her own reviews about the particular product which can also be viewed by other customers.SenticNet is a publicly available resource for opinion mining that exploits AI, linguistics, and psychology to infer thepolarity associated with common-sense concepts and encodes this in a semantic-aware representation. In particular,SenticNet uses dimensionality reduction to calculate the affective valence of multi-word expressions and, hence,represent it in a machine accessible and machine- process able format. This chapter presents an overview of the mostrecent sentic computing tools and techniques, with particular focus on applications in the context of big social dataanalysis. We propose a weakly supervised system that achieves a reasonable performance improvement over thebaseline without requiring any tagged training data.
