Abstract
Higher Education has a role of developing the socioeconomic status of nations through human capital development, building and use of knowledge as well as research development. Since the inception of South African democracy, the vision of the South African government has been to realize ‘a better life for all’ through economic development by regenerating an entire social system through production of skilled graduates. This drive was accomplished by implementation of the Reconstruction and Development Program (RDP) introduced in 1994. Despite the government's efforts, it is however alarming to see the higher education sector in shambles due to student protests. The student protests result to destruction of university infrastructure and are affecting students' academic performance negatively. The protests do not only affect academic activities, but also impact the South African economy negatively due to the bad publicity that is presented by the protests. Developing models that would predict the students' protests would be a positive contribution towards prevention of such protests. Machine learning techniques are well known for producing accurate predictive models. This study therefore explored machine learning techniques to build a students' protests prediction model. The study used support vector machine technique for the implementation. Data collected from news articles and social media was used to train and test the prediction model. The accuracy of the prediction model was evaluated using split validation technique. The results of the study indicated that the proposed algorithm can accurately model the prediction of the students' strikes. The orchestrated experiments involved comparing the accuracy of two SVM kernels, viz, the RBF and the Linear kernels. The results have revealed that the RBF kernel remarkably outperforms the linear kernel.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.