Sustainability 2023, 15(7), 6229; https://0-doi-org.brum.beds.ac.uk/10.3390/su15076229 - 04 Apr 2023
Cited by 2 | Viewed by 3854
Abstract
►
Show Figures
The process of learning about a student’s knowledge and comprehension of a particular subject is referred to as student knowledge assessment. It helps to identify areas where students need additional support or challenge and can be used to evaluate the effectiveness of instruction,
[...] Read more.
The process of learning about a student’s knowledge and comprehension of a particular subject is referred to as student knowledge assessment. It helps to identify areas where students need additional support or challenge and can be used to evaluate the effectiveness of instruction, make important decisions such as on student placement and curriculum development, and monitor the quality of education. Evaluating student knowledge assessment is essential to measuring student progress, informing instruction, and providing feedback to improve student performance and enhance the overall teaching and learning experience. This research paper is designed to create a machine learning (ML)-based system that assesses student performance and knowledge throughout the course of their studies and pinpoints the key variables that have the most significant effects on that performance and expertise. Additionally, it describes the impact of running models with data that only contains key features on their performance. To classify the students, the paper employs seven different classifiers, including support vector machines (SVM), logistic regression (LR), random forest (RF), decision tree (DT), gradient boosting machine (GBM), Gaussian Naive Bayes (GNB), and multi-layer perceptron (MLP). This paper carries out two experiments to see how best to replicate the automatic classification of student knowledge. In the first experiment, the dataset (Dataset 1) was used in its original state, including all five properties listed in the dataset, to evaluate the performance indicators. In the second experiment, the least correlated variable was removed from the dataset to create a smaller dataset (Dataset 2), and the same set of performance indicators was evaluated. Then, the performance indicators using Dataset 1 and Dataset 2 were compared. The GBM exhibited the highest prediction accuracy of 98%, according to Dataset 1. In terms of prediction error, the GBM also performed well. The accuracy of optimistic forecasts on student performance, denoted as the performance indicator ‘precision’, was highest in GBM at 99%, while DT, RF, and SVM were 98% accurate in their optimistic forecasts for Dataset 1. The second experiment’s findings demonstrated that practically no classifiers showed appreciable improvements in prediction accuracy with a reduced feature set in Dataset 2. It showed that the time required for related learning objects and the knowledge level corresponding to a goal learning object have less impact.
Full article
Figure 1
