期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2018
卷号：96
期号：8
出版社：Journal of Theoretical and Applied
摘要：Twitter Sentiment Classification is one of the most popular fields in information retrieval and text mining. Thousand of millions of people around the world intensity use web sites such as Twitter. Twitter, as a micro-blogging system, allows users to publish tweets to tell others what they are thinking. In fact, there are already many web sites built on the Internet providing a Twitter sentiment search service. In those web sites, the user can input a sentiment target and in searching for tweets containing positive and negative sentiments. As a result of the increasing number of tweets over the past few years, tweets have attracted more and more attention. This is striking for consumers to research the sentiment of products before purchase automatically. This paper proposes a novel model for Twitter Sentiment Classification. The purpose of this model is investigating what is the role of weighting feature techniques in Sentiment Classification using supervised methods on the Twitter data set. Also, it explores binary classification which is classified data set into positive and negative classes. It is shown that usage of the proposed model can improve 7% the accuracy of Twitter Sentiment Classification. The results confirmed the superiority of the proposed model over the state-of-the-art systems.
关键词：Sentiment Classification; Support Vector Machine; Supervised Method; Twitter
