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：6
页码：11910
DOI：10.15680/IJIRCCE.2017.0506098
出版社：S&S Publications
摘要：The utilization of web 2.0 as a platform has made the web a treasure trove of sentiments. People aroundthe world express and share their opinions and reactions on web regarding day-to-day activities and global issues aswell thus making a huge amount of intelligent data available to all. With this vast wealth of data arises the need forautomatic opinion classification. Sentiment classification using machine learning algorithms faces the problem of highdimensionality of feature space. Therefore, a feature selection method is used to eliminate the uncounted features fromthe word vector space for efficiency improvement to machine learning approaches. In this paper, we intend to applyGA and swarm optimization (i.e., PSO) technique to optimize the feature selection. We exemplify our proposed methodon the online movie reviews using sentiment analysis approach. SVM is proposed for sentiment classification. Fromexperimental results it can be ascertained that combined approach i.e., PSO-GA gives better classification accuracycompared to PSO-based method. PSO provides the advantages in providing the solution to discrete problems.
