Predicting the Influence of Internet on Students’ Academic Performance Using Decision Tree (DT) and Support Vector Machine (SVM) Classification Algorithms

Oparah Vivian O; Agbakwuru AO; Eleberi E L; Amanze BC

doi:10.56201/ijcsmt.vol.11.no6.2025.pg108.120

📄 Download Paper

Predicting the Influence of Internet on Students’ Academic Performance Using Decision Tree (DT) and Support Vector Machine (SVM) Classification Algorithms

Oparah Vivian O,Agbakwuru AO,Eleberi E L, and Amanze BC

Abstract

The aim of this paper is to develop a predictive model using the Decision Tree (DT) and Support Vector Machine (SVM) classification machine learning algorithms that can identify the effects constant use or addiction of the internet towards students’ academic performance. The internet was selected as the major predictor which could help to predict the role of internet in academic success or downfall of a student. The experiment was conducted on a dataset named (Student_data.csv) sourced from kaggle machine learning repository. The dataset comprises of 395 data with 33 features which internet is chosen as the target feature. The dataset was split into train 316 and test 79 respectively in other to achieve a more accurate prediction. The analysis employed two machine learning classification algorithms namely: Support Vector Machine (SVM) and Decision Tree (DT) while employing R language and JASP platform for the experiment. The results produced by the decision tree algorithm showed a model with 80% accuracy which serves as a great predictive model on decision making towards students’ academic performance of 284 indicators saying YES on the constant use of Internet as one of the major factor influencing academic performance of students while 32 indicators saying NO. The second experiment conducted with SVM algorithm produced a model with a predicted accuracy rate of 0.873 (87%) with a total 129 support vectors hyper plane model distribution from the dataset of 316 train. Finally, the two produced model was compared after checking the different F1 scores, confusion matrix and Precision (positive predictive value) Through the Evaluation Metrics table and Andrews Curve Plot Model and ROC Curves model.

Keywords

Artificial IntelligenceMachine LearningAcademic Performance Classification

References

1. Kumar (2011). Efficiency of decision trees in predicting student’s academic performance.. 2. Baker and Yacef (2009). The state of educational data mining: A review and future visions. Journal of educational data mining 1.1 (2009): 3-17. 3. Ventura and Romero, (2013). Predicting students final performance from participation in online discussion forums. Computers & Education 68 (2013): 458-472. 4. Amin (2023). The Use of CNN, LSTM Algorithm, and Attention Mechanism for Predicting student performance. World Scientific Reports 1.1 (2023): 21-41. 5. Sivasakthi (2022). Prediction of students programming performance using naïve bayesian and decision tree. Soft Computing for Security Applications: Proceedings of ICSCS 2022. Singapore: Springer Nature Singapore, 2022. 97-106. 6. Fan Yanga, Yang, Fan, and Frederick WB Li (2018). Study on student performance estimation, student progress analysis, and student potential prediction based on data mining. Computers & education 123.: 97-108. 7. Safri, Safari, Mahmood, and Nader Soleimani (2018). The relationship between teachers’ academic optimism culture and student achievement in junior high schools in Tehran. Biannual Journal of Education Experiences 1.2 (2019): 43-58. 8. Huda (2017). Investigating Factors Influencing Mathematics Teaching Performance: An Empirical Study. International Journal of Instruction 11.3 (2018): 391-402. 9. Kabakchieva, Kabakchieva, Dorina (2013). Predicting student performance by using data mining methods for classification. Cybernetics and information technologies 13.1. 61-72. 10. Ramesh (2013) . Predicting student performance: a statistical and data mining approach. International journal of computer applications 63.8 (2013). 11. Tekin (2014). Early prediction of students’ grade point averages at graduation: A data mining approach. Eurasian Journal of Educational Research 54 (2014): 207-226. 12. Gray , Sarah, Anne (2017). Qualitative review synthesis: The relationship between inattention and academic achievement. Educational Research : 17-35. Artificial neural network model for prediction of students’ success in learning programming. Journal of Scientific & Industrial Research 80.03 (2021): 249-254. 13. Asif (2015) . Analyzing undergraduate students performance using educational data mining. Computers & education 113 (2017): 177-194. 14. Parneet (2015). Classification and prediction based data mining algorithms to predict slow learners in education sector. Procedia Computer Science 57 (2015): 500-508. 15. Fadhilah (2015). The prediction of students’ academic performance using classification data mining techniques. Applied mathematical sciences 9.129 (2015): 6415-6426. 16. Jishan, Jiawei Han and Micheline Kamber, (2017) . Data Mining Concepts and Techniques, Morgan Kauffman Publishers. 17. Yan, Y., Omisore, O. M., Xue, Y. C., Li, H. H., Liu, Q. H., Nie, Z. D, & Wang, L. (2020). Classification of neurodegenerative diseases via topological motion analysis. A comparison study for multiple gait fluctuations. IEEE Access, 8, 96363-96377.

Predicting the Influence of Internet on Students’ Academic Performance Using Decision Tree (DT) and Support Vector Machine (SVM) Classification Algorithms

Abstract

Keywords

References

More Articles from INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND MATHEMATICAL THEORY