Mooc course recommendation system model with explainable AI (XAI) using content based filtering method.

Praseptiawan, Mugi and Muchtarom, M. Fikri Damar and Puteri, Nabila Muthia and Che Pee @ Che Hanapi, Ahmad Naim and Zakaria, Mohd Hafiz and Untoro, Meida Cahyo (2024) Mooc course recommendation system model with explainable AI (XAI) using content based filtering method. In: 2024 11th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI), 26-27 2024.

Text
Mooc Course Recommendation System Model with Explainable AI (XAI) Using Content Based Filtering Method.pdf
Download (353kB)

Official URL: https://doi.org/10.1109/EECSI63442.2024.10776491

Abstract

Abstract— Massive Open Online Course (MOOC) is a type of online course that has been designed and can be accessed by all individuals via the internet. The problem that is often found in MOOCs is the lack of a recommendation system provided by the algorithm of the MOOC. This research is conducted to analyze a recommendation system that applies the Content Based Filtering approach in order to solve the problems that occur. The recommendation system analyzed will function as a media that provides recommendations to users based on their preferences. By utilizing content-based methods, the recommendations given are expected to be exactly what the user wants. The level of explainability of the recommendation system is further emphasized by XAI using ELI5. By getting a concise explanation when a recommendation is given, the system will gain more trust from users for providing an appropriate recommendation. The assessment of the accuracy of the recommendation system model is measured using MAE. By researching this recommendation system using XAI, it is hoped that it can help future systems to improve the quality of the course recommendation system.

Item Type:	Conference or Workshop Item (Paper)
Divisions:	Faculty of Information and Communication Technology
Depositing User:	NURHASHIRAH BORHAN
Date Deposited:	31 Jul 2026 07:29
Last Modified:	31 Jul 2026 07:29
URI:	http://eprints.utem.edu.my/id/eprint/30120
Statistic Details:	View Download Statistic

Actions (login required)

View Item