• Sandeep Kaur
• Pardeep Kumar

People usually express emotions in various forms such as speech, facial expressions and text. Analyzing human emotions in text has grabbed a lot of attention, nowadays. This research work explores ways to automatic extraction of emotions in social media text. The text under research deals with data collected from Twitter, representing data rich in affective content. Corpus is specifically prepared on Demonetization. Demonetization was one of the decisions made by the Prime Minister Narendra Modi in 2016. Nevertheless, people were not aware of this action and they expressed their views and opinions that rich in sentiments and emotive content on social media such as Twitter. Efficient machine controversial learning algorithms Naïve Bayes and Support Vector machines have been used for automatic classification of emotions. Moreover, the accuracy achieved with SVM is 90.13%, however with that of Naïve Bayes is 85.03%. Furthermore, valuable inferences have been drawn from the real time tweets of demonetization that reveal that anger, fear, surprise and sadness are mostly expressed emotions over this issue.

Affective computing, Emotion Analysis, Naïve Bayes, Support Vector Machines.

" Emotion Extraction System on real time Demonetization Tweets using Machine Learning ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 11, page no.37-43, November 2018, Available :http://www.jetir.org/papers/JETIRDR06006.pdf

" Emotion Extraction System on real time Demonetization Tweets using Machine Learning ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 11, page no. pp37-43, November 2018, Available at : http://www.jetir.org/papers/JETIRDR06006.pdf