A PRAGMATIC TEXT MINING ANALYSIS OF DEMONETISATION MOVE BASED ON TOPIC MODEL AND TWITTER COMMUNICATIONS

Main Article Content

Doddi Srilatha
Shirisha Kakarla

Abstract

Demonetisation move has been the most trending topic on the twitter during the recent months. Indian government had taken a sudden decision to phase out the two most high valued denominations of Rupees 500 and 1000 currency notes. This decision was observed with different sentiments among the various sects of the people in the society. It caused sensation in the whole country. In this paper, we considered tweets related to demonetisation move and the speech contents that were delivered by the premier of the country. The significant number of tweets are downloaded, preprocessed to remove the noise like re-tweets, analyzed using frequency analysis and a topic model using Latent Dirichlet Allocation (LDA) is constructed. The LDA model automatically discovered the most relevant topics. Further clustering is done to project the clear view of the citizens’ and especially the public leaders’ opinions on this move. The most of the topics were related to criticize the Prime Minister’s speech addressed to the nation on new year event, although few opined the benefits of demonetisation.

Downloads

Download data is not yet available.

Article Details

Section
Articles

References

Hashtag: https://en.wikipedia.org/wiki/Hashtag

Blei, David, "Probabilistic Topic Models". Communications of the ACM. 55 (4): PP:77–84. doi:10.1145/2133806.2133826 , 2012.

D. Blei and J. Lafferty. Topic Models. Text Mining: Theory and Applications, 2009.

D. Ramage, S. Dumais, and D. Liebling. Characterizing Microblogs with Topic Models. In International AAAI Conference on Weblogs and Social Media, 2010.

David M. Ble, Andrew Y. Ng, and Michael I. Jordan, Latent Dirichlet Allocation, Journal of Machine Learning Research 3, 993-1022, 2003.

R Studio: https://www.rstudio.com/