Affect Analysis of Multilingual Tweets for Predicting Voting Behavior
Lata Gohil1, Dharmendra Patel2

1Lata Gohil*, Computer Science and Engineering Department, Institute of Technology, Nirma University, India, Smt. Chandaben Mohanbhai Patel Institute of Computer Applications (CMPICA), CHARUSAT, Changa, India.
2Dharmendra Patel, Smt. Chandaben Mohanbhai Patel Institute of Computer Applications (CMPICA), CHARUSAT, Changa, India.

Manuscript received on November 15, 2019. | Revised Manuscript received on 20 November, 2019. | Manuscript published on December 10, 2019. | PP: 1768-1771 | Volume-9 Issue-2, December 2019. | Retrieval Number: B7742129219/2019©BEIESP | DOI: 10.35940/ijitee.B7742.129219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Social media has been proved as wild card for its role in election campaign across the globe. It has been used for general election of India in year 2014 and year 2019 by political parties for election campaign. Thus social media provides opportunity for electoral prediction. Users from India use regional languages in addition to English language on social media. Multilingual data likely to give better prediction compared to single language data. Affect analysis gives deeper insight compared to sentiment analysis. This research study aims to predict voting behavior for 2019 general election of India using affect analysis of multilingual tweets. Three languages namely English, Hindi and Gujarati are used for this study. Volume-based method and machine learning algorithm based method are two approaches widely used in literature for electoral prediction. In this research study hybrid approach is used along with consideration of ratio of positive count and negative count of tweets. Experiment result shows efficacy of the proposed approach. 
Keywords: Multilingual, Social Media, Twitter, Emotion Analysis, Sentiment Analysis, Opinion Mining, Election
Scope of the Article: Behaviour of Structures