Investigating Digital Divide Barriers, Institutional Support, and Students’ Perceptions of AI-Driven Mathematics Learning

Abstract

Integration of artificial intelligence (AI) into mathematics education holds significant potential to enhance learning outcomes; however, its effectiveness in resource-constrained higher education contexts remains uneven due to persistent digital divide barriers. This quantitative study investigates how socioeconomic status shapes first-level (technology access) and second level (digital skills and institutional support) digital divide barriers, and how these factors relate to students’ perceptions of AI-driven mathematics learning. Grounded in van Dijk’s digital divide theory, a cross-sectional survey was administered to 121 undergraduate mathematics students at a historically disadvantaged higher education institution. Descriptive statistics, Pearson correlation, and Chi-square analyses were employed to examine associations among socioeconomic status, access, skills, institutional support, and AI perceptions. The findings indicate that material access barriers, such as limited devices and internet connectivity, remain prevalent among disadvantaged students but show weak or inconsistent associations with perceptions of AI. In contrast, institutional support demonstrates a statistically significant positive relationship with students’ perceptions of AI training (r = 0.212, p < 0.05), highlighting its central role in shaping readiness for AI-enhanced learning. Overall, the results suggest that second-level digital divide factors, particularly structured institutional support, are more influential than access alone in determining students’ engagement with AI in mathematics education. The study implies the need for universities to move beyond infrastructure provision toward comprehensive and sustained institutional strategies that foster confidence, guided engagement, and equitable AI adoption.