Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal International Journal of Advances in Data and Information Systems
Mochamad Imamudin
Departmen of Informatics Engineering, Maulana Malik Ibrahim State Islamic University of Malang, Indonesia
Computer Science & IT Electrical & Electronics Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Towards Explainable Multidimensional Digital Divide Classification in Online Learning Using Artificial Neural Networks and SHAP Imalatul Hidayah; Ririen Kusumawati; Mochamad Imamudin
International Journal of Advances in Data and Information Systems Vol. 7 No. 2 (2026): August 2026 - International Journal of Advances in Data and Information Systems
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59395/ijadis.v7i2.1666

Abstract

The transformation of online learning increases access to education, but also increases the risk of digital divide influenced by various technological and educational factors. This study aims to develop a framework Towards Explainable Multidimensional Digital Divide Classification in Online Learning Using Artificial Neural Networks and SHAP to classify cluster-derived digital divide categories transparently. Data were obtained from 324 students through a questionnaire covering Primary Device, Internet Stability, Equity Score, and Accessibility Score. The target Digital Divide categories were analytically derived using K-Means clustering based on respondents' multidimensional characteristics and subsequently used as labels for supervised classification. The data were processed through one-hot encoding, Min-Max normalization, and splitting the training and test data before training the model. The performance of ANN was compared with Logistic Regression, Decision Tree, Random Forest, and Support Vector Machine (SVM). The results showed that ANN achieved 90.77% accuracy, with competitive performance against the comparison models. Furthermore, SHapley Additive exPlanations (SHAP) was used to interpret the model's decisions at both global and local levels. The analysis shows that Primary Device is the most influential factor, followed by Accessibility Score, Equity Score, and Internet Stability. The main contribution of this research is the presentation of an Explainable AI framework that combines the predictive capabilities of ANN with the interpretability of SHAP to support a more transparent multidimensional digital divide classification and can serve as a basis for developing data-driven digital inclusion policies.
Co-Authors Imalatul Hidayah Ririen Kusumawati