Topic modelling of the “fix the country” protest in Ghana using the Latent Dirichlet Allocation (LDA) and Jaccard Similarity approach

Authors

  • Bryan N. Lartey Laryea Author
  • Kenneth Asiamah Author
  • Alhassan Michael Araphat Author
  • Elisha A. Mensah Author
  • Edwin K. Tsekpo Author
  • Anne Breh Hawa Author
  • Sandra Sawdiatu Inusah Author

Keywords:

Jaccard Similarity, Topic modelling, Social media analysis, Latent Dirichlet Allocation (LDA) , Protest movements

Abstract

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.

Author Biographies

  • Bryan N. Lartey Laryea

    Bryan Laryea is a Researcher at CSIR- Institute of Technological Information. He is also a Lecturer at Knutsford University College. He has consulted for projects in public and private sectors such as Ghana’s National Information Technology Authority and Vodafone Ghana. He has a master’s in Management Information Systems. His main research areas are Information Systems and Development of Bots for crowdsourcing data.

  • Kenneth Asiamah

    Mr. Kenneth Asiamah is an ICT professional with an MSc and BSc in Information and Communication Technology Management. He's an Assistant Research Scientist at CSIR – INSTI, focusing on cutting-edge research and the development of innovative tools and systems. Kenneth's technical expertise extends to web development, computer systems administration, and fundamentals of data security. He's committed to industry knowledge, earning the Google IT Support Professional Certificate in 2023.

  • Alhassan Michael Araphat

    Alhassan Michael Araphat is a Computer Engineer with MSc. And BSc. In Computer Systems and Networks. He is an Assistant Research Scientist at CSIR- INSTI focusing on cutting Edge research and the development of innovative tools and systems. Michael’s Technical expertise extends to Software development including Mobile and Web applications, Computer Networking and Systems. He is committed to exploring and adapting to upcoming technology trends.

  • Elisha A. Mensah

    Elisha Mensah is a versatile research assistant at the Council for Scientific and Industrial Research (CSIR), blending expertise in health sciences and technology. Elisha's work spans public health, social science, and health technology. Elisha employs data-driven approaches to address societal challenges. Proficient in web development, robotics, and front-end engineering, Elisha's interdisciplinary skills drive innovation. With well-honed communication skills, Elisha bridges research and practice, translating findings for impact. Committed to excellence, Elisha's research aims for tangible benefits in communities.

  • Edwin K. Tsekpo

    Edwin Tsekpo has a background in computer engineering, Edwin brings expertise in software development and data analysis to the team.  Proficient in programming languages and data analytics tools, Edwin's technical skills drive innovation in research projects. Through interdisciplinary collaboration, Edwin combines engineering principles with research methodologies to tackle diverse topics. His commitment to excellence ensures high-quality outcomes in every project he undertakes. Passionate about leveraging technology for social impact, Edwin's work contributes to the advancement of knowledge and societal well-being.

  • Anne Breh Hawa

    Anne Breh Hawa

    A library assistant and technical editor with Council for Scientific and Industrial Research – Institute for Scientific and Technological Information (CSIR-INSTI). She holds a B.A in Information Studies from the University of Ghana. Aside her professional work she does translations, transcriptions and Jingles.

  • Sandra Sawdiatu Inusah

    Sandra Sawdiatu Inusah is BSc. Natural Resources Management graduate from the Kwame Nkrumah University of Science and Technology Ghana. She is currently working with the Alliance of Bioversity International and CIAT in Accra Ghana as a geospatial analyst. Her research interest lies in landscape ecology, human-environment interactions, and integrating geospatial and machine learning technologies into environmental conservation. Specifically, she

    wants to integrate geospatial and machine-learning technologies into research projects that can improve environmental conservation decision-making.

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.

Downloads

Published

06/13/2024

How to Cite

Laryea, B., Asiamah, K., Alhassan, M. ., Mensah, E., Tsekpo, E., Hawa, A., & Inusah, S. (2024). Topic modelling of the “fix the country” protest in Ghana using the Latent Dirichlet Allocation (LDA) and Jaccard Similarity approach. Journal of Applied Science and Information Technology, 1(1). https://csirjasit.org/index.php/journal/article/view/5