期刊名称：International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
印刷版ISSN：2278-1323
出版年度：2015
卷号：4
期号：6
页码：2987-2990
出版社：Shri Pannalal Research Institute of Technolgy
摘要：In Recent Years, the use of smart phones and mobile applications has been increased, as it generate large amount of data which can be in text or speech format, we have to deal with that data so there is need for sentiment classification to use that data in useful way. In this paper we are using phrases and words as a feature for sentiment classification of product reviews. Here the goal of this paper is to find a statistical way representative words and phrases that are used typically in positive and negative reviews. Here we are using two dataset first is Product Review and another is Movie Review and we are comparing the results of these datasets. The approach is based on machine learning approach; here machine learning techniques are used to classify the sentiment into positive or negative instead of predefined lexicon based approach. The motivation is that potentially each word or phrase could be considered as expressing something positive or negative in different case.
关键词：Sentiment Analysis; Opinion Extraction; ; Machine Learning; Phrase Extraction; Distinctiveness of ; Phrase; Scoring Algorithm; Support Vector Machine (SVM).
