Twitter Sentiment Analysis using Machine Learning Techniques
K. Sentamilselvan1, D. Aneri2, A. C. Athithiya3, P. Kani Kumar4
1Mr.K.Sentamilselvan*, Assistant Professor, Department of Information Technology, Kongu Engineering College, Erode.
2Ms. D. Aneri, Final Year Student, Department of Information Technology, Kongu Engineering College, Erode.
3Ms. A.C. Athithiya, Final Year Student, B. Tech IT, Kongu Engineering College, Erode.
4Mr. P. Kani Kumar, Final Year Student, B. Tech Information Technology, Kongu Engineering College, Erode.
Manuscript received on January 21, 2020. | Revised Manuscript received on February 05, 2020. | Manuscript published on February 29, 2020. | PP: 4205-4209 | Volume-9 Issue-3, February 2020. | Retrieval Number: C6281029320/2020©BEIESP | DOI: 10.35940/ijeat.C6281.029320
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: Nowadays people share their views and opinions in twitter and other social media platforms, the way of recognizing sentiments and speculation in tweets is Twitter Sentiment Analysis. Determining the contradiction or sentiment of the tweets and then listing them into positive, negative and neutral tweets is the main classifying step in this process. The issue related to sentiment analysis is the naming of the correct congruous sentiment classifier algorithm to list the tweets. The foundation classifier techniques like Logistic regression, Naive Bayes classifier, Random Forest and SVMs are normally used. In this paper, the Naïve Bayes classifier and Logistic Regression has been used to perform sentiment analysis and classify based on the better accuracy of catagorizing Technique. The outcome shows that Naive Bayes classifier works better for this approach. Data pre-processing and feature extraction is realized as a portion of task.
Keywords: Feature extraction, Logistic regression, multinomial Naïve Bayes, Sentiment Analysis.