INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
Predicting the results of the 15th Karnataka Legislative Assembly Elections using Twitter
Authors Name:
Chaitanya Agarwal
Unique Id:
IJSDR1810016
Published In:
Volume 3 Issue 10, October-2018
Abstract:
With 330 million MAU’s (Monthly Active Users) at the beginning of 2018, Twitter has been crowned the 13th most popular website in the world. Twitter as a data source is highly regarded due to its popularity and its infrastructure that provides almost 100% of its data through the API. Along with its own, third party libraries have immensely contributed to the growth of Twitter as a source of information. Users are limited to post 280 characters per tweet, which often fall under numerous categories ranging from sports to politics. These tweets are suitable for various purposes such as research, analysis, marketing, campaigning and more. The goal of this paper is to provide a comparative analysis between the prediction obtained from twitter and the opinion polls held with regards to the Karnataka State Elections, and to highlight the feasibility of using social media to predict opinions, rather than the traditional methods of polling .I have crawled thousands of tweets with the help of Tweepy. Tweets are classified based on the location of origin or location the tweet is directed to. Using Natural Language Processing, each tweet is classified based on whether it was positive or negative with respect to the major political parties in the respective states.
Keywords:
Twitter, NLP, State Election, Prediction
Cite Article:
"Predicting the results of the 15th Karnataka Legislative Assembly Elections using Twitter", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.3, Issue 10, page no.105 - 109, October-2018, Available :http://www.ijsdr.org/papers/IJSDR1810016.pdf
Downloads:
000346980
Publication Details:
Published Paper ID: IJSDR1810016
Registration ID:180703
Published In: Volume 3 Issue 10, October-2018
DOI (Digital Object Identifier):
Page No: 105 - 109
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn