EUVIMEDEUVIMED entdecken
Crossref

A Machine Learning-Based Peer Tutoring Web Application for Intelligent Tutor–Student Matching

Fatade Oluwayemisi Boye, Ukwute Chukwudumebi Nkemakolem, Towolawi Ayomide Fadilulahi, Pinwa Joshua Nwibari

International Journal of Advanced Research in Science Communication and Technology · 18.08.2026 · 707

DOI: 10.48175/ijarsct-38069 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Advanced Research in Science Communication and Technology, online erschienen am 18.08.2026. Verfasst von Fatade Oluwayemisi Boye und 3 weiteren Autor:innen. Die Arbeit nennt 15 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Peer tutoring is a widely recognized strategy for improving academic performance, yet most existing platforms rely on manual or rule-based pairing methods that may not fully account for individual learner needs, tutor expertise, and historical interaction outcomes. This study presents the development of a peer tutoring web application based on machine learning algorithms for automatic tutor–student matching using a Random Forest classifier. The application was developed using a modular software architecture including a React.js front end, Flask back-end API, and a PostgreSQL relational database. The matching algorithm was trained on a synthetic dataset of interactions between tutors and students, which included features such as average student improvement rate, tutor rating, compatibility of subjects, experience level, and session outcomes. The classifier’s hyperparameters were tuned using GridSearchCV across multiple parameter combinations. Functional evaluation showed that all critical system functionalities, such as user registration, tutor–student matching, session booking, asynchronous messaging, and rating submission, performed as expected. The machine learning algorithm achieved a classification accuracy of 81%, with balanced precision and recall metrics for both classes, exceeding the accuracy of random assignment. These results suggest that supervised learning can support personalized tutor recommendations within a peer tutoring platform.

Zitieren

APA

Boye, F. O., Nkemakolem, U. C., Fadilulahi, T. A., & Nwibari, P. J. (2026). A Machine Learning-Based Peer Tutoring Web Application for Intelligent Tutor–Student Matching. International Journal of Advanced Research in Science Communication and Technology, 707. https://doi.org/10.48175/ijarsct-38069

Vancouver

Boye FO, Nkemakolem UC, Fadilulahi TA, Nwibari PJ. A Machine Learning-Based Peer Tutoring Web Application for Intelligent Tutor–Student Matching. International Journal of Advanced Research in Science Communication and Technology. 2026:707. doi:10.48175/ijarsct-38069

BibTeX
@article{Boye2026,
  author = {Boye, Fatade Oluwayemisi and Nkemakolem, Ukwute Chukwudumebi and Fadilulahi, Towolawi Ayomide and Nwibari, Pinwa Joshua},
  title = {A Machine Learning-Based Peer Tutoring Web Application for Intelligent Tutor–Student Matching},
  journal = {International Journal of Advanced Research in Science Communication and Technology},
  year = {2026},
  pages = {707},
  doi = {10.48175/ijarsct-38069}
}
Kostenlos starten →