The own-race bias effect in South Africa

Researcher: Inonge Lupinda, University of the Witwatersrand, Johannesburg
Supervisors: Dr Colin Tredoux, University of Cape Town and Dr Helen Robertson, University of the Witwatersrand, Johannesburg


Face recognition is critical for human connection and perceptual ability, and mistakes in face recognition can degrade the quality of social interaction. Own-race bias (ORB) in facial recognition refers to the tendency to recognize people from one’s own racial group more accurately than people from other racial groupings. This research examines the prevalence and presence of the ORB phenomena in human face recall, its various explanations, and causes, and the serious implications it has in eyewitness cross-racial identification, using a South African demographic of Black, White, and Coloured people. It explores how social inclusion or exclusion exacerbates this phenomenon, especially considering the historical context of South Africa. Embedded in ORB are social-cognitive factors such as implicit bias, racial attitudes, social motivation, and the contact hypothesis.

Read More

Good Governance is the Driving Force for Participation Amongst IGO’s & TGI’s

Researcher: Octavia Ndlovu, University of the Witwatersrand, Johannesburg
Supervisor: Prof. Oliver Westerwinter, University of the Witwatersrand, Johannesburg

Link to YouTube Video


This paper gives a foundation to the first of many research paper that look into testing the relationship between good governance and the participation of Intergovernmental organisations in the type of Transnational governance initiatives. I hope to achieve these results through the use of two data sets that will be merged for the best results and that is using Transnational Public-Private Governance Initiatives in World Politics Data, together with data from Worldwide Governance Indicator. This paper doesn’t hope to achieve much beyond the scales of knowing if good governance is the reason of the participation og so much Intergovernmental organisation, I hope the results of this paper will help policy makers into making policies that will help benefit the world at a global scale, where IGOs have a good governance reason for being a part of TGIs.

Read More

Indigenous Women Moving From Physical to Digital Fires: The Evolution of Methods of Transmission of Indigenous Knowledge

Researcher: Khanyisile Yolanda Ntsenge, University of the Witwatersrand, Johannesburg
Supervisors: Dr Constance Khupe and Prof. Rod Alence, University of the Witwatersrand, Johannesburg

In response to the threat of extinction of indigenous knowledge, there has been a growing number of people, a significant amount of whom are women, interested in the preservation of indigenous knowledge systems who have begun to use social media platforms such as Twitter and YouTube and the indigenous method of storytelling to share indigenous knowledge.
The aim of the study is to understand how the introduction of the social media platforms Twitter and YouTube has changed the community structures for sharing indigenous knowledge in physical versus social media communities.

The research is informed by a postcolonial indigenous and indigenous feminist approach and employs transformative participatory research in its methodology. Indigenous women in physical communities participated in the research while accounts owned by indigenous women on Twitter and YouTube were analysed. A social network analysis was conducted on both the physical communities data and social media data. Sentiment analysis was conducted on the social media data.

The results show that the network of communities while both anchored by indigenous women have different structures. The physical communities were very tight-knit with members of the networks learning and sharing indigenous knowledge amongst each other thereby potentially reinforcing their knowledge. The social media communities were mainly connected only to the main account and members rarely engaged with each other. The sentiment analysis found conversations in the social media networks to be significantly positive with the highest scoring emotion being that of trust.

The research has shown that although women play an important role in the sharing of indigenous knowledge in both physical and online communities, the community network structures differ. It also evidenced that there is a space and appetite for conversations on indigenous knowledge on social media. Furthermore, as they are in physical communities, women continue to be important custodians of indigenous knowledge and are trusted to share credible indigenous knowledge. This presents opportunities for further exploration on how to leverage social media platforms to mainstream indigenous knowledge while amplifying the voices of indigenous women as custodians of indigenous knowledge.

View the full report

Read More

Academic Journals

Bonnet, W. & Celik, T. 2021. Random Sampling-Based Relative. IEEE Geoscience and Remote Sensing Letters. 9321136:1–4.Byamugisha, J., Saib, W., Gaelejwe, T., Jeewa, A., & Molapo, M. (2020a). Abstract PR-12: Towards verifying results from biomedical deep learning models using the UMLS: Cases of primary tumor site classification and cancer Named Entity Recognition. Association for the Advancement of Artificial Intelligence, PR-12-PR-12. https://doi.org/10.1158/1557-3265.adi21-pr-12

Byamugisha, J., Saib, W., Gaelejwe, T., Jeewa, A., & Molapo, M. (2020b). Towards Verifying Results from Biomedical NLP Machine Learning Models Using the UMLS: Cases of Classification and Named Entity Recognition. www.aaai.org

Chabumba, D.R., Jadhav, A. & Ajoodha, R. 2021. Predicting Telecommunication Customer Churn using Machine Learning Techniques. Interdisciplinary Research in Technology and Management. (September, 14):625–636.

Choma, J., Correa, F., Dahbi, S.-E., Dwolatzky, B., Dwolatzky, L., Hayasi, K., Lieberman, B., Maslo, C., et al. (in press). Worldwide Effectiveness of Various Non-Pharmaceutical Intervention Control Strategies on the Global COVID-19 Pandemic: A Linearised Control Model. medRxiv. (May, 12):2020.04.30.20085316.

Daniel, L.O., Sigauke, C., Chibaya, C. & Mbuvha, R. 2020. Short-term wind speed forecasting using statistical and machine learning methods. Algorithms. 13(6).

Essa, Y., Hunt, H. G. P., Gijben, M., & Ajoodha, R. (2022). Deep Learning Prediction of Thunderstorm Severity Using Remote Sensing Weather Data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15(June), 4004–4013. https://doi.org/10.1109/JSTARS.2022.3172785

Freeborough, W. & van Zyl, T. 2022. Investigating Explainability Methods in Recurrent Neural Network Architectures for Financial Time Series Data. Applied Sciences (Switzerland). 12(3):1–15.

Freeborough, W., Gentle, N. & Rey, M.E.C. 2021. WRKY Transcription Factors in Cassava Contribute to Regulation of Tolerance and Susceptibility to Cassava Mosaic Disease through Stress Responses. Viruses. 13(1820).

Harling, G., Gómez-Olivé, F.X., Tlouyamma, J., Mutevedzi, T., Kabudula, C.W., Mahlako, R., Singh, U., Ohene-Kwofie, D., Mahlako R., et al. 2021. Protective behaviors and secondary harms resulting from nonpharmaceutical interventions during the COVID-19 epidemic in South Africa: Multisite, prospective longitudinal study. JMIR Public Health and Surveillance. 7(5):1–17.

Mabunda, J.G.K., Jadhav, A. & Ajoodha, R. 2021. Sentiment Analysis of Student Textual Feedback to Improve Teaching. in Interdisciplinary Research in Technology and Management CRC Press. 643–651.

Masangu, L., Jadhav, A. & Ajoodha, R. 2021. Predicting student academic performance using data mining techniques. Advances in Science, Technology and Engineering Systems. 6(1):153–163.

Mutavhatsindi, T., Sigauke, C. & Mbuvha, A.R. 2020. Forecasting hourly global horizontal solar irradiance in South Africa using machine learning models. IEEE Access. 8:198872–198885.

Ngwenduna, K.S. & Mbuvha, R. 2021. Alleviating class imbalance in actuarial applications using generative adversarial networks. Risks. 9(3):1–33.

Nkolele, R. 2020. Mapping of Narrative Text Fields To ICD-10 Codes Using Natural Language Processing and Machine Learning. in Proceedings of the The Fourth Widening Natural Language Processing Workshop Association for Computational Linguistics (ACL). 131–135.

Orievulu, K. S. (2020). (Re-engaging) the “tyranny” of process in participatory development programming in Africa: Fadama in Nigeria as a case study. South African Journal of International Affairs, 27(2), 243–264. https://doi.org/10.1080/10220461.2020.1785930

Ratshilengo, M., Sigauke, C. & Bere, A. 2021. Short-term Solar Power Forecasting using Genetic Algorithms: An Application using South African Data. Applied Sciences (Switzerland). 11(9).

Ohamadike, Nnaemeka, Orakwe, E.C. “The Role of Education in the Public Perception of Corruption in Sudan and Zimbabwe”. Politeia, 11 pages . https://doi.org/10.25159/2663-6689/13663.

Read More

Evaluating banking customer churn Deep Learning model (Deep Neural Network) in terms of explainability

Researcher: Hlayisani Khoza, University of Limpopo
Supervisor: Dr Hairong Bau, University of the Witwatersrand, Johannesburg

In the financial industry forecasting, client attrition is critical. The expense of hiring fresh clients is significantly greater than the expense of maintaining current clients. There are several Machine Learning (ML) models in use to forecast client attrition, and the results are impressive. The issue with these models is their lack of openness and interpretability. Deep Learning (DL) models are the leading models in this development because of the layered non-linear structure, which provides no insight into how they reach at their results, these strong models have been dubbed “Black Boxes”. To deal with this problem Explainable methods have been used to explain these model outcomes. In this research, Shapley Additive method has been applied to the Multilayer Perceptron model to explain its result and it has been found to explain banking customer churn better.


Read More

International Commitments and domestic enforcement against drugs

Researcher:  Raquel Baeta, University of the Witwatersrand, Johannesburg
Supervisor:  Dr Oliver Westerwinter, University of the Witwatersrand, Johannesburg

State commitment to the Single Convention on Narcotic Drugs of 1961, the Convention on Psychotropic Substances of 1971, and the Convention against Illicit Drugs and Psychotropic Substances of 1988 influence domestic regulations and the rate of drug seizures.


Read More

Climate Change and Agricultural Production in Developing Countries

Researcher:  Tshepiso Segone, University of the Witwatersrand, Johannesburg
Supervisor:  Prof. Rod Alence, University of the Witwatersrand, Johannesburg

Agricultural development in developing countries is essential for alleviating poverty. Compared to developing countries, the rate of agricultural development in developing countries is drastically delayed. Climate-related threats to agricultural production can disturb economic processes and welfare.


Read More

Application of Machine Learning Algorithms for Rainfall Forecasting in KwaZulu Natal Province, South Africa

Researcher:  Jeremiah Ogunniyi, Sol Plaatje University
Supervisor:  Dr Ibidun Obagbuwa , Sol Plaatje University

This study applied three machine learning algorithms namely Linear Regression (LR), Random Forest (RF), and Support Vector Machine (SVM) to predict precipitation in KwaZulu Natal Province, South Africa. The result shows that SVM had the best performance followed by RF and finally LR.


Read More

Assessing Financing for Climate Change Mitigation and Adaptation for Developing Countries

Researcher:  Puseletso Maile, University of the Witwatersrand, Johannesburg
Supervisor:  Prof. Rod Alence, University of the Witwatersrand, Johannesburg

In 2010 leaders from developed nations pledged to contribute a $100 billion year on year towards climate finance for developing countries. The reason for this is because developed countries are the biggest polluters and because developing countries are most vulnerable to climate change and because they do not have the resources to respond to extreme weather conditions.  This study assesses trends in climate finance for developing countries looking at whether: There was a significant increase in climate finance after 2010. Trends in climate finance at regional level and income group level. If climate finance provided for mitigation was higher than for adaptation. And what are determinants for climate finance.

This study applied three machine learning algorithms namely Linear Regression (LR), Random Forest (RF), and Support Vector Machine (SVM) to predict precipitation in KwaZulu Natal Province, South Africa. The result shows that SVM had the best performance followed by RF and finally LR.


Read More

Prediction of breast cancer using machine learning algorithms

Researcher:  Sedzani Ndou, University of Venda
Supervisors:  Prof. O. Olugbenga

Breast cancer is a deadly disease mostly in women’s health all over the world, as it is considered the second most deadly cancer after lung cancer.  To predict breast cancer we implement six different algorithms. We try to pick the best algorithm for this purpose by comparing their performance accuracy. What is/are the most effective machine learning algorithms for predicting and diagnosing breast cancer?


Read More