In today’s technological world, a majority of users across the world have access to Internet for communication via text, image, audio and video. People from diverse backgrounds exchange information on current scenarios and project their own views on them over social media. There is a need to understand and recognize the behavior of such large text information on people by analyzing their emotions. The paper focuses on data obtained from one of the most popular social media - Twitter by analyzing live as well as past feeds and getting emotions from them. The twitter data required in English language is converted into a vector of eight emotions and supervised learning techniques such as K-means, Naive Bayes and SVM is used to determine label identifying one of the basic emotion family. At the end, a comparative study of the performance of different classifiers is discussed.

sentiment, machine learning, emotion detection, twitter, SVM, Naive Bayes

[1] Bing Liu (2009) Sentiment Analysis and Subjectivity, Handbook of Natural Language Processing, Second Edition (editors: N. Indurkhya and FJ Damerau)
[2] Santhoshi Kumari, Narendra Babu, Real Time Analysis of Social Media Data to Understand People Emotions Towards National Parties, 8th ICCCNT 2017, July 3 - 5, 2017, IIT Delhi, Delhi.
[3] Ekman, P (1992), An Argument for Basic emotions, Cognition and Emotion, 6(3-4), (Pg. - 169-200).
[4] Sentiment Analysis of Social Networking Sites Data using Machine Learning Approach for the Measurement of Depression, Anees Ul Hassan, Jamil Hussain, Sungyoung Lee, ICTC 2017, (Pg. - 138-140)
[5] Saima Aman and Stan Szpakowicz (2007), Identifying Expressions of Emotion in Text, V. Matouek and P. Mautner (Eds.): TSD 2007, LNAI 4629, pp. 196205, 2007. Springer-Verlag Berlin Heidelberg 2007
[6] Livia Polanyi and Annie Zaenen (2006), Contextual Valence Shifters, Computing attitude and affect in text: Theory and applications, (Pg. 1-10)
[7] Plank B, Hovy D (2015), Personality Traits on Twitter-or How to get 1,500 Personality Tests in a Week, In 6th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis (WASSA 2015) (Pg. 92)
[8] Lionel Martin and Pearl Pu (2014), Prediction of Helpful Reviews Using Emotions Extraction. AAAI Conference on Artificial Intelligence Twenty-Eight AAAI Conference on Artificial Intelligence.
[9] Soumaya Chaffar and Diana Inkpen (2011) Using a Heterogeneous Dataset for Emotion Analysis in Text, Proceeding Canadian AI11 Proceedings of the 24th Canadian Conference on Advances in Artificial Intelligence (Pg. 62-76).
[10] Emotion and Polarity Prediction from Twitter, Rebeen A Hamad, Saeed Alqahtani Mercedes Torres, Computing Conference 2017, 18-20 July 2017, London UK, (Pg. 297-306)
[11] Exploring Human emotion via Twitter, Abu Z Riyadh, Nasif Alvi, Kamrul Hasan, 2017 20th International Conference on Computer and Information Technology (ICCIT), 22-24 December 2017.
[12] Emotion Detection from the SMS of the Internet, Uma N, Priyanka K, Aditi M, Dr. Dhananjay K., 2013 IEEE Recent Advances in Intelligent Computational Systems (RAICS). (Pg. 316 - 321)
[13] Twitter Sentiment Analysis and Opinion Mining, Ravikiran Janardhana, Dept. of CSE, University of North Carolina.
[14] Framework for Emotion Detection and Classification of English and Non-English Tweets, Anup Prasad and Mayank Jaglan, Indiana University Bloomington, School of Informatics and Computing.