Data-Driven Approaches to Enhancing Students’ Web Design Skills Using Multimodal Learning Analytics

Abstract

This study investigates data-driven approaches to enhancing students’ web design skills through the integration of multimodal learning analytics (MLA) within adaptive digital learning environments. As the complexity of digital competencies continues to increase, there is a growing need for innovative, data-informed instructional strategies that support personalized and efficient learning processes. The research adopts a mixed-method design, combining quantitative analysis of learning analytics data with qualitative observations of learner behavior. The results demonstrate that MLA-based adaptive systems significantly improve student engagement, skill acquisition, and overall learning efficiency. By leveraging multimodal data sources, the proposed approach enables real-time feedback, personalized learning pathways, and more accurate assessment of competence development. The study contributes to the advancement of intelligent, data-driven educational systems and offers practical implications for improving the quality of web design education in higher education contexts.