A Comparative Study of Twitter Sentiment Analysis Using Machine Learning Algorithms in Big Data
C. Bagath Basha1, K. Somasundaram2
1C. Bagath Basha, Research Scholar, Department of Computer Science Engineering, Vinayaka Mission’s Research Foundation, Salem, (Tamil Nadu), India.
2Dr. K. Somasundaram, Professor, Department of Computer Science Engineering, Aarupadai Veedu Institute of Technology, Vinayaka Mission’s Research Foundation, Salem, (Tamil Nadu), India.

Manuscript received on 19 April 2019 | Revised Manuscript received on 26 May 2019 | Manuscript published on 30 May 2019 | PP: 591-599 | Volume-8 Issue-1, May 2019 | Retrieval Number: F2580037619/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© 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: In recent years, the data growth has suddenly increased through social media like Twitter, Facebook, YouTube, etc., because everyone has used. These unstructured data is used to handle various applications in data analytics. These applications are used for public opinion and sentiment analysis (POSA) in Twitter by various Machine Learning (ML) Algorithms. In this paper, mainly discuss about Twitter sentiment analysis and Machine Learning Algorithms. We take the sample tweets from Twitter, and finding the positive, negative, and neutral words, and then will make it polarity score by using Twitter Sentiment analysis. Using this data are applying ML algorithms. This algorithm is used to show the comparison result between Random Forest (RF) algorithm and Classification algorithm to know which one is best performance. Random Forest algorithm is good when compare with Classification algorithm. Classification algorithm is best for easy understanding. Finally in this social media have low level of security in the Twitter data.
Index Terms: Big Data, Machine Learning, Twitter

Scope of the Article: Machine Learning