Topic modelling of the “fix the country” protest in Ghana using the Latent Dirichlet Allocation (LDA) and Jaccard Similarity approach
Keywords:
Jaccard Similarity, Topic modelling, Social media analysis, Latent Dirichlet Allocation (LDA) , Protest movementsAbstract
The surge in protest movements worldwide highlights the growing dissatisfaction among citizens and their determination to voice concerns and demand change. This study examines the "Fix the Country" protest in Ghana, which gained significant momentum in 2021, providing a platform for Ghanaians to express grievances regarding issues such as corruption, unemployment, and inadequate infrastructure. This research aims to uncover the key topics and themes emerging from the "Fix the Country" protest discourse and analyze the engagement patterns of participants across these identified topics. Employing topic modelling techniques, specifically Latent Dirichlet Allocation (LDA) and the Jaccard Similarity approach, this study systematically analyzes dataset of tweets collected during the protest period. The LDA analysis revealed dominant themes centered on leadership, socio-economic issues, the role of the president, the "#FixTheCountry petition," and general discontent. Furthermore, the Jaccard Similarity analysis categorized tweets into predefined topics, with Health-related tweets garnering the largest share (81.303%), followed by Economic and Cultural topics (6.22% each), and Social topics (6.25%). The findings contribute to the academic understanding of protest movements, social media analysis, shedding light on the underlying dynamics and concerns that drive collective action. Furthermore, the study's insights hold significant implications for policymakers and inform future interventions aimed at addressing the issues raised during the "Fix the Country" protest.
References
Abramova, O., Batzel, K., & Modesti, D. (2022). Collective response to the health crisis among German Twitter
users: A structural topic modeling approach. International Journal of Information Management Data
Insights, 2(2), 100126.
Asante, L. A., & Helbrecht, I. (2018). Seeing through African protest logics: A longitudinal review of continuity and
change in protests in Ghana. Canadian Journal of African Studies/Revue canadienne des études africaines, 52(2), 159–181.
Brobbery, C. A. B., Da-Costa, C. A., & Apeakoran, E. N. (2021). The communicative ecology of social media in
The Organization of Social Movement for collective action in Ghana: The case of#
fixthecountry. Information
Impact: Journal of Information and Knowledge Management, 12(2), 73–86.
Bond, P., & Mottiar, S. (2013). Movements, protests and a massacre in South Africa. Journal of Contemporary
African Studies, 31(2), 283–302.
Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent dirichlet allocation. Journal of machine Learning
research, 3(Jan), 993–1022.
Bukhari, F. A. S., Rana, O. F., & Naqvi, H. (2018). Analysing and modelling public sentiment in social media.
ACM Transactions on Internet Technology (TOIT), 18(1), 1–25.
Chen, Y., Peng, Z., Kim, S. H., & Choi, C. W. (2023). What we can do and cannot do with topic modeling: A
systematic review. Communication Methods and Measures, 17(2), 111–130.
Das, S., Sun, X., & Dutta, A. (2016). Text mining and topic modeling of compendiums of papers from transportation
research board annual meetings. Transportation Research Record, 2552(1), 48–56.
Gatti, C. J., Brooks, J. D., & Nurre, S. G. (2015). A historical analysis of the field of or/ms using topic models. arXiv
preprint arXiv:1510.05154.
Lansley, G., & Longley, P. A. (2016). The geography of Twitter topics in London. Computers, Environment and
Urban Systems, 58, 85–96.
Lim, K. W., Chen, C., & Buntine, W. (2016). Twitter-network topic model: A full Bayesian treatment for social
network and text modeling. arXiv preprint arXiv:1609.06791.
Laouni, N. E. (2022). Cyberactivism and protest movements: the February 20th movement–the forming of a new
generation in Morocco. The Journal of North African Studies, 27(2), 296–325.
Oh, Y. W. & Kim, J. (2023). Insights Into Korean Public Perspectives on Urology: Online News Data Analytics
Through Latent Dirichlet Allocation Topic Modeling. International Neurourology Journal, 27(Suppl 2), S91.
Ortiz, I., Burke, S., Berrada, M., Saenz Cortés, H., Ortiz, I., Burke, S., & Saenz Cortés, H. (2022). An analysis
of world protests 2006–2020. World protests: A study of Key protest issues in the 21st century, 13–81.
Schmiedl, M., & Lioy, A. (2024). Patterns of Protest in Contemporary Africa: An Empirical Investigation of Regional
Trends Employing Multiple Imputation. Political Studies Review, 14789299241239913.
Sun, L., & Yin, Y. (2017). Discovering themes and trends in transportation research using topic
modeling. Transportation Research Part C: Emerging Technologies, 77, 49–66.
Tufekci, Z., & Wilson, C. (2012). Social media and the decision to participate in political protest: Observations from
Tahrir Square. Journal of Communication, 62(2), 363–379.
Theocharis, Y., Boulianne, S., Koc-Michalska, K., & Bimber, B. (2023). Platform affordances and political
participation: how social media reshape political engagement. West European Politics, 46(4), 788–811.
Thelwall, M., & Buckley, K. (2013). Topic‐based sentiment analysis for the social web: The role of mood and issue‐
related words. Journal of the American Society for Information Science and Technology, 64(8), 1608–1617.
Yang, M. C., & Rim, H. C. (2014). Identifying interesting Twitter contents using topical analysis. Expert Systems
with Applications, 41(9), 4330–4336.
Zhao, W. X., Jiang, J., Weng, J., He, J., Lim, E. P., Yan, H., & Li, X. (2011). Comparing twitter and traditional
media using topic models. In Advances in Information Retrieval: 33rd European Conference on IR Research, ECIR 2011, Dublin, Ireland, April 18–21, 2011. Proceedings 33, 338–349 Springer Berlin Heidelberg.
