Prediction of Student Academic Performance Based on Their Emotional Wellbeing and Interaction on Various E-Learning Platforms

Autor/inn/en	Kukkar, Ashima; Mohana, Rajni; Sharma, Aman; Nayyar, Anand
Titel	Prediction of Student Academic Performance Based on Their Emotional Wellbeing and Interaction on Various E-Learning Platforms
Quelle	In: Education and Information Technologies, 28 (2023) 8, S.9655-9684 (30 Seiten)Infoseite zur Zeitschrift PDF als Volltext Verfügbarkeit
Zusatzinformation	ORCID (Nayyar, Anand)
Sprache	englisch
Dokumenttyp	gedruckt; online; Zeitschriftenaufsatz
ISSN	1360-2357
DOI	10.1007/s10639-022-11573-9
Schlagwörter	Academic Achievement; Mental Health; Well Being; Interaction; Electronic Learning; Higher Education; College Students; Prediction; Accuracy; Models; Artificial Intelligence; Tests; Outcomes of Education; Algorithms; Bayesian Statistics + Suchen Sie Ihr Suchwort? Schulleistung; Psychohygiene; Well-being; Wellness; Wohlbefinden; Interaktion; Hochschulbildung; Hochschulsystem; Hochschulwesen; Collegestudent; Vorhersage; Analogiemodell; Künstliche Intelligenz; Examination; Prüfung; Examen; Lernleistung; Schulerfolg; Algorithm; Algorithmus
Abstract	Predicting student performance is crucial in higher education, as it facilitates course selection and the development of appropriate future study plans. The process of supporting the instructors and supervisors in monitoring students in order to upkeep them and combine training programs to get the best outcomes. It decreases the official warning signs and inefficient students' expulsions. Therefore, analysis of students' performance on various academic tests is critical for future skill development. Despite the fact that existing performance prediction systems based on Deep Learning (DL) technologies such as Artificial Neural Networks (ANN), Recurrent Neural Network (RNN) have outperformed Machine Learning (ML) -based systems in the prediction task, there are still a few issues. Ignorance of relevant features, analysis limitations to the existing amount of data points, and ambiguity in student records are only a few of these issues. This research proposes a novel Student Academic Performance Predicting (SAPP) system to address these issues and enhance prediction accuracy. It has a better architecture that uses a combination of 4-layer stacked Long Short Term Memory (LSTM) network, Random Forest (RF), and Gradient Boosting (GB) techniques to predict students' pass or fail outcomes. Additionally, the proposed SAPP system is compared to existing prediction systems using publicly accessible student OULAD dataset with an addition of self-curated emotional dataset. The performance of SAPP system is measured using Accuracy, Precision, F-measure, and Recall parameters. The results of proposed algorithm (LSTM + RF + B) is compared with LSTM + RF, LSTM + B and end to end DL models such as ANN, LSTM, RNN, Convolutional Neural Network (CNN) and most commonly utilized ML models in the literature such as Support Vector Machine (SVM), Decision Tree (DT), Naive Bayes (NB) and RF. The proposed SAPP system gained approximately 96% prediction accuracy that is comparatively higher than existing systems. (As Provided).
Anmerkungen	Springer. Available from: Springer Nature. One New York Plaza, Suite 4600, New York, NY 10004. Tel: 800-777-4643; Tel: 212-460-1500; Fax: 212-460-1700; e-mail: customerservice@springernature.com; Web site: https://link.springer.com/
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2024/1/01