International Journal of Computer Science and Mechatronics A peer reviewed international journal | Article available at http://ijcsm.in | SJIF 6.19 ©smsamspublications.com | Vol.7.Issue.6.2021.ISSN: 2455-1910 1 | P a g e ©smsamspublications.com Emotion Recognition on Twitter: Comparative Study and Training a Unison Model G. Yamini Satish 1 , M. Ashok Kumar 2 , K Sudhakar 3 Assistant Professor 1 , Associate Professor & HoD 2 , Associate Professor Department of CSE, Vikas College of Engineering & Technology, A.P., India. Department of CSE, PSCMR College of Engineering and Technology Abstract — In this paper, propose designing a sentiment analysis by extracting a vast number of tweets. Prototyping is used in this development. Results classify customers' perspective via tweets into positive, negative and neutral, which is represented in an html web page. However, the program has planned to develop on a web application system, using Natural Language Processing and Deep Learning integrated with JSP, Servlet web stack. Keywords — social media, Twitter, Emotion Recognition. I. INTRODUCTION Due to the vast number of texts, manual inspection for emotion classification is infeasible, hence the need for accurate automatic systems. Although in many cases people can easily spot whether the author of a text was angry or happy, the task is quite challenging for a computer - mainly due to the lack of background [2]knowledge that is implicitly considered by humans. Given some text, emotion recognition algorithms detect which emotions the writer wanted to express when composing it. To treat this problem as a special case of text classification, we need to define a set of basic emotions. Although emotions have long been studied by psychologists, there is no single, standard set of basic emotions. Therefore, we decided to work with three classifications that are the most popular, and have also been used beforeby the researchers from computational linguistics and natural language processing (NLP). [ 4 ] Paul Ekman defined six basic emotions by studying facial expressions. Robert Plutchik extended