TEXTUAL SENTIMENT TRENDS IN PAKISTAN: BUILDING AN INDEX USING NEWS REPORTS AND SOCIAL MEDIA DISCOURSE
DOI:
https://doi.org/10.56596/jrefm.v3i2.153Keywords:
Text-Based Sentiment Index, Natural Language Processing (NLP), Machine Learning, Public Opinion, Trend AnalysisAbstract
This research develops the Text-Based Sentiment Index (TBSI) to measure public sentiment through the evaluation of English-language newspaper content alongside social media posts. An analysis of media sentiment specifically focuses on utilizing textual data from Dawn, The News International, Express Tribune, and Twitter posts during the period from 2012 to 2024. The combination of the VADER sentiment tool and machine learning techniques performed sentiment classification in this study. The research demonstrated that extensive public emotional responses occurred during pivotal national events when major elections took place, as well as during periods of leadership changes and economic transformations, alongside the COVID-19 pandemic outbreak. The research data supports established hypotheses, which confirm that public conduct reveals itself through media sentiment while media sentiment predicts future public behavior. Researchers developed an index from monthly sentiment scores, which served as a tool for policy determinations that proved helpful to political decision-makers as well as academic and institutional groups. Sentiment analysis requires extension beyond English-language content since resource constraints prevented processing Urdu and Roman Urdu texts.
References
Afzaal, M. (2020). The China-Pakistan economic corridor of the Belt and Road Initiative concept, context, and assessment, Taylor & Francis.
Ahmad, W., & Edalati, M. (2022). Urdu speech and text-based sentiment analyzer. arXiv Preprint arXiv:2207.09163.
Al Jazeera. (2017, July 28). Pakistan Supreme Court disqualifies Nawaz Sharif. Al Jazeera. https://www.aljazeera.com/news/2017/7/28/pakistan-supreme-court-disqualifies-nawaz-sharif
Aslam, N., Nadeem, A., Abid, M. K., & Fuzail, M. (2023). Text-Based Sentiment Analysis Using CNN-GRU Deep Learning Model. Journal of Information Communication Technologies and Robotic Applications, 14(1), 16–28.
Baqir, A., Galeazzi, A., Drocco, A., & Zollo, F. (2023). Social media polarization reflects shifting political alliances in Pakistan. arXiv Preprint arXiv:2309.08075.
Baqir, A., Galeazzi, A., Drocco, A., & Zollo, F. (2023). Social media polarization reflects shifting political alliances in Pakistan. arXiv Preprint, arXiv:2309.08075.
BBC. (2012, June 19). Pakistan Supreme Court bars PM Gilani from office. BBC. https://www.bbc.com/news/world-asia-18506728
Diego García. (2013). Sentiment during Recessions. The Journal of Finance, 68(3), 1267–1300. https://doi.org/10.1111/jofi.12027
Haroon, D., Arif, H., Tariq, A. A., & Qazi, I. A. (2021). Investigating Misinformation Dissemination on Social Media in Pakistan. arXiv Preprint arXiv:2106.09338.
Hutto, C. J., & Gilbert, E. (2014). VADER: A parsimonious rule-based model for sentiment analysis of social media text. Proceedings of the International AAAI Conference on Web and Social Media, 8(1), 216–225.
Irum, A., & Tahir, M. A. (2025). Document-Level Sentiment Analysis of Urdu Text Using Deep Learning Techniques. arXiv Preprint arXiv:2501.17175.
Kausar, S., Tahir, B., & Mehmood, M. A. (2021). Towards understanding the manipulation of trends in Pakistan on Twitter. arXiv Preprint arXiv:2109.14872.
Khan, S., Moqurrab, S. A., Sehar, R., & Ayub, U. (2018). Opinion and emotion mining for Pakistan general election 2018 on Twitter data, 98–109.
Khattak, A., Asghar, M. Z., Saeed, A., Hameed, I. A., Hassan, S. A., & Ahmad, S. (2021). A survey on sentiment analysis in Urdu: A resource-poor language. Egyptian Informatics Journal, 22(1), 53–74.
Kumari, S., Rafaqat, S., & Shabbir, T. (2025). Misuse of Social Media: Impacts on Pakistan Politics. Pakistan Social Sciences Review, 9(1), 131–143.
Liaqat, M. I., Hassan, M. A., Shoaib, M., Khurshid, S. K., & Shamseldin, M. A. (2022). Sentiment analysis techniques, challenges, and opportunities: Urdu language-based analytical study. PeerJ Computer Science, 8, e1032.
Mughal, S., Jaffar, A., & Arif, M. W. (2024). Sentiment Analysis of Social Media Data: Understanding Public Perception. Journal of Computing & Biomedical Informatics, 7(02).
Mukhtar, N., & Khan, M. A. (2020). An effective lexicon-based approach for Urdu sentiment analysis. Artificial Intelligence Review, 53(4), 2521–2548.
Nagra, A. A., Abubakar, M., Warsi, S. U., Mohsin, S., & Abdullah, H. (2024). Pakistan’s Political Sentiments Analysis based on Twitter Using Machine Learning. Journal of Computing & Biomedical Informatics, 6(02), 13–22.
Noor, H., Ahmad, J., Haider, A., Nasim, F., & Jaffar, A. (2024). A Machine Learning Sentiment Analysis Approach on News Headlines to Evaluate the Performance of the Pakistani Government. Journal of Computing & Biomedical Informatics, 7(02).
Pak Institute for Peace Studies. (2021). Pakistan Security Report 2020. https://www.pakpips.com/web/wp-content/uploads/2021/01/Conflict-and-Peace-Studies.pdf
Pang, B., & Lee, L. (2008). Opinion mining and sentiment analysis. Foundations and Trends® in Information Retrieval, 2(1–2), 1–135.
Qayyum, A., Gilani, Z., Latif, S., & Qadir, J. (2018). Exploring media bias and toxicity in south asian political discourse, 01–08.
Shiller, R. J. (2015). Irrational Exuberance: Revised and Expanded Third Edition. Princeton University Press. https://books.google.com.pk/books?id=_
aIpBQAAQBAJ
Tetlock, P. C. (2007). Giving content to investor sentiment: The role of media in the stock market. The Journal of Finance, 62(3), 1139–1168
Tumasjan, A., Sprenger, T. O., Sandner, P. G., & Welpe, I. M. (2010). Predicting elections with Twitter: What 140 characters reveal about political sentiment. Proceedings of the Fourth International AAAI Conference on Weblogs and Social Media, 178–185.
Downloads
Published
Issue
Section
License

This work is licensed under a Creative Commons Attribution 4.0 International License.
This work published in the journal is licensed under a Creative Commons Attribution 4.0 International License
.

