Classification of Sentiment on Business Data for Decision Making using Supervised Machine Learning Methods
Siji George C G1, B. Sumathi2
1Siji George C G*, Ph.D. Scholar, CMS College of Science and Commerce, Coimbatore, Tamil Nadu, India.
2Dr. B. Sumathi, Associate Professor, CMS College of Science and Commerce, Coimbatore, Tamil Nadu, India.
Manuscript received on January 23, 2020. | Revised Manuscript received on February 05, 2020. | Manuscript published on February 30, 2020. | PP: 3595-3600 | Volume-9 Issue-3, February 2020. | Retrieval Number: C6086029320 /2020©BEIESP | DOI: 10.35940/ijeat.C6086.029320
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Sentiment analysis is deals with the classification of sentiments expressed in a particular document. The analysis of user generated data by using sentiment analysis is very useful for knowing the opinion of a crowd. This paper is mainly aimed to tackle the problem of polarity categorization of sentiment analysis. A Detailed description of the sentiment analysis process is also given. Product review data set from UCI repository is used for analysis. This paper is giving a comparative analysis of four supervised machine learning algorithms namely Naive Bayes, Support Vector Machine, Decision Tree and Random Forest which are used for product review analysis. The result shows that, Random Forest classification algorithm provides better accuracy than other three algorithms.
Keywords: Decision Tree, Naive Bayes , Random Forest ,Sentiment Analysis, , Support Vector Machine(SVM).