Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Predicting grade progression within the Limpopo Education System
One way to improve education in South Africa is to ensure that additional support and resourcing are provided to schools and learners that are most in need of help. To this end, education officials need to understand the factors affecting learning and the schools most in need of appropriate interven...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
Department of Computer Science
2019
|
| Tags: |
No Tags, Be the first to tag this record!
|
| Summary: | One way to improve education in South Africa is to ensure that additional support and resourcing are provided to schools and learners that are most in need of help. To this end, education officials need to understand the factors affecting learning and the schools most in need of appropriate interventions. Several theories, models and methods have been developed to attempt to address the challenges faced in the education sector. Educational Data Mining (EDM) is one which has gained prominence in addressing these challenges. EDM is a field of data mining using mathematical and machine learning models to improve learners’ performance, education administration, and policy formulation. This study explored the literature and related methodologies used within the EDM context and constructed a solution to improve learner support and planning in the Limpopo primary and secondary schools education system. The data utilized included socio-economic environment, demographic information as well as learner’s performance sourced from the Education Management Information Systems database of the Limpopo Department of Education (LDoE). Feature selection methods; Information Gain, Correlation and Asymmetrical Uncertainty were combined to determine factors that affect learning. Three machine learning classifiers, AdaboostM1 (Decision Stump), HoeffdingTree and NaïveBayes, were used to predict learners’ grade progression. These were compared using several evaluation metrics and HoeffdingTree outperformed AdaboostM1 (Decision Stump) and NaïveBayes. When the final HoeffdingTree model was applied to the test datasets, the performance was exceptionally good. It is hoped that the implementation of this model will assist the LDoE in its role of supporting learning and planning of resource allocation. |
|---|