Authors : Mrinmay Deb; Soumen Bhowmik

Volume/Issue : Volume 11 - 2026, Issue 3 - March

Google Scholar : https://tinyurl.com/4hmuh4xb

Scribd : https://tinyurl.com/yzv9rkym

DOI : https://doi.org/10.38124/ijisrt/26mar043

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : This study looks at how the sentiment of media texts can help explain and support the precision of election exit poll results. It collects news and broadcast material related to an election, uses sentiment analysis methods to categorize opinions about the main parties or candidates, and then compares these sentiment patterns with exit poll forecasts and actual results. By quantifying the alignment or divergence between media sentiment, exit poll estimates, and actual results, the work evaluates whether systematically measured media tone can explain exit poll errors, highlight potential biases, and provide an auxiliary signal for assessing the credibility of election-night forecasts. This study aims to evaluate the predictive capacity of social media in forecasting the results of the 2024 lok sabha elections in West Bengal before the election took place, especially during the campaign time. This work orients by collecting a substantial volume of social media data through web crawling techniques, utilizing data analysis methods, comprehending sentiment analysis and machine learning, applied to evaluate the relationship between tweet volume, sentiment polarity, and electoral outcomes. This study aims to establish if engagement on social media can be a viable metric in determining election outcomes. This study will add to the existing literature on computational analysis of politics and social media-based election crystal gazing and provide insights on the impact of digital conversations in a democracy.

Keywords : Artificial Intelligence, Machine Learning, Deep Learning, Natural Language Processing, Explainable Artificial Intelligence, Social Media Trends, Political Forecasting, Lok Sabha Elections.

References :

1. Role of media surveys in predicting and shaping the exit poll and opinion polls outcome -https://www.socialsciencejournal.in/assets/archives/2020/vol6issue6/6-6-38-490.pdf
2. THANOS: A Predictive Model of Electoral Campaigns Using Twitter Data and Opinion Polls - https://www.tandfonline.com/doi/full/10.1080/26941899.2025.2484180?scroll=top&needAccess=true
3. Exit Polling: Elections and the Media Lesson - CT.gov https://portal.ct.gov/media/SOTS/Capitol2011to2015/WhyVotingMatters/SecIV/ExitPollingElectionsandtheMediapdf.pdf
4. What are Exit Polls and How are they Conducted? - CivilsDaily https://www.civilsdaily.com/news/what-are-exit-polls-and-how-are-they-conducted/
5. Opinion Polls, Exit Polls, Poll of Polls: What makes them different? https://www.indiatoday.in/elections/story/exit-polls-vs-opinion-polls-vs-poll-of-polls-difference-explained-2817537-2025-11-11
6. Exit Polls - Drishti IAS https://www.drishtiias.com/daily-updates/daily-news-analysis/exit-polls
7. Exit Polls Strategies for Political Campaigns in India https://politicalpartyregistration.co.in/exit-polls-strategies-political-campaigns-india/
8. Exit Polls - ACE Electoral Knowledge Network https://aceproject.org/main/english/me/med07c01.htm
9. Exit poll - Wikipedia https://en.wikipedia.org/wiki/Exit_poll
10. [PDF] WAPOR GUIDELINES FOR EXIT POLLS AND ELECTION https://wapor.org/wp-content/uploads/WAPOR-Guidelines-for-Exit-Polls-and-Election-Forecasts.pdf
11. Exit Polls: Role In Electoral System, Analysis, And Regulations https://pwonlyias.com/exit-poll/
12. Capturing Significant Information Regarding Election Result Using Twitter Data https://link.springer.com/chapter/10.1007/978-3-032-02790-0_13
13. Barber´a, P. “How Social Media Reduces Mass Political Polarization: Evi- dence from Germany, Spain, and the U.S.” American Journal of Political Science, 2015.
14. ntscraper: A Python package for scraping Twitter data. Version 0.1.1. Available at: https://pypi.org/project/ntscraper/0.1.1/.
15. Jungherr, A. (2016). ”Twitter use in election campaigns: A systematic literature review.” Journal of Information Technology & Politics, 13(1), 72-91.
16. Tumasjan, A., Sprenger, T. O., Sandner, P. G., & Welpe, I. M. (2010). ”Pre- dicting elections with Twitter: What 140 characters reveal about political sentiment.” Proceedings of the Fourth International AAAI Conference on Weblogs and Social Media, 178-185.
17. O’Connor, B., Balasubramanyan, R., Routledge, B. R., & Smith, N. A. “From Tweets to polls: Linking text sentiment to public opinion time se- ries.” Proceedings of the International AAAI Conference on Weblogs and Social Media, 122-129, 2010.
18. Barber´a, P., & Rivero, G. “Understanding the political representativeness of Twitter users.” Social Science Computer Review, 33(6), 712-729, 2015.
19. Mohammad, S., Kiritchenko, S., & Zhu, X. “NRC-Canada: Building the state-of-the-art in sentiment analysis of tweets.” Proceedings of the Interna- tional Workshop on Semantic Evaluation (SemEval-2013), 321-327, 2013.
20. Ferrara, E., Varol, O., Davis, C., Menczer, F., & Flammini, A. “The rise of social bots.” Communications of the ACM, 59(7), 96-104, 2016.