EUVIMEDEUVIMED entdecken
Crossref

Decoding ChatGPT’s impact on student satisfaction and performance: a multimodal machine learning and explainable AI approach

Nisar Ahmed Dahri, Fida Hussain Dahri, Asif Ali Laghari, Muhammad Javed

Complex Engineering Systems · 29.05.2025 · 5 (2)

DOI: 10.20517/ces.2025.07 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Complex Engineering Systems, online erschienen am 29.05.2025. Verfasst von Nisar Ahmed Dahri und 3 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 75 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The extensive use of artificial intelligence (AI) tools in education and their effectiveness and explicability have become an essential area of investigation because of their scope for ethical and fair use. Therefore, this innovative approach proposed a multimodal machine learning and explainable AI (XAI) approach to predict how ChatGPT’s usage impacts students’ academic outcomes, including satisfaction and performance. Three machine learning models, XGBoost, Random Forest, and Support Vector Machine, were used to predict students’ performance and level of satisfaction. The XAI techniques, SHapley Additive exPlanations and Local Interpretable Model-Agnostic Explanations, were used to investigate how models make decisions with ethical standards and ensure models are reliable and fair in their usage. A custom-created dataset, ChatGPT Survey Data, was utilized for the experiment. All three models gave the promised classification, with Support Vector Machine having the highest accuracy at 89% and the receiver operating characteristic curve and the area under this curve (AUC-ROC) at 92%. Random Forest has 87% accuracy and an AUC-ROC of 90%. XGBoost showed the best accuracy with 92% (R2). XAI analysis revealed ChatGPT usage and satisfaction as key predictors of academic performance, advancing AI’s role in education.

Zitieren

APA

Dahri, N. A., Dahri, F. H., Laghari, A. A., & Javed, M. (2025). Decoding ChatGPT’s impact on student satisfaction and performance: a multimodal machine learning and explainable AI approach. Complex Engineering Systems, 5(2). https://doi.org/10.20517/ces.2025.07

Vancouver

Dahri NA, Dahri FH, Laghari AA, Javed M. Decoding ChatGPT’s impact on student satisfaction and performance: a multimodal machine learning and explainable AI approach. Complex Engineering Systems. 2025;5(2). doi:10.20517/ces.2025.07

BibTeX
@article{Dahri2025,
  author = {Dahri, Nisar Ahmed and Dahri, Fida Hussain and Laghari, Asif Ali and Javed, Muhammad},
  title = {Decoding ChatGPT’s impact on student satisfaction and performance: a multimodal machine learning and explainable AI approach},
  journal = {Complex Engineering Systems},
  year = {2025},
  volume = {5},
  number = {2},
  doi = {10.20517/ces.2025.07}
}
Kostenlos starten →