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：2019
卷号：97
期号：6
页码：1704-1719
出版社：Journal of Theoretical and Applied
摘要：Handle Negation is essential for effective sentiment analysis decision support system. Negation control comprised identification of negation cues, scope of negation and their influence within it. Negation can either invert, reduce or increase the polarity score. This paper present comprehensive assessment of recent research on negation control for sentiment analysis technique. Explore negation cue and scope detection techniques in collaboration with classification technique over social media data set. This assessment has included the evaluation of sentiment classification (Support vector machine, Navies Bayes, Linear Regression and Random Forest) and scope detection techniques (conjunction Analysis, Punctuation Mark and grammatical dependency tree) over presented prepossessing framework. This paper yield interesting result about collective response of negation scope detection and classification technique for sentiment analysis. Negative scope feature vector significantly increase the polarity classification accuracy of sentiment classification technique. Grammatical dependency tree in collaboration with SVM and Naves Bayes can detect negation with better accuracy as compere to conjunction and punctuation word scope detection technique.
关键词：Sentiment Analysis; Negation Cues; Scope Detection; Conjunction Analysis; Punctuation Mark; Grammatical Dependency Tree; Navies Bayes; Linear Regression; Random Forest; SVM
