Towards a Proposed Instructional Model for Harnessing Generative Artificial Intelligence to Personalize Arabic Language Teaching for Non-Native Speakers in Light of Cognitive Load Theory

Abstract

This study aims to develop a proposed instructional model for employing Generative Artificial Intelligence (GenAI) to personalize Arabic language learning for non-native speakers in light of Cognitive Load Theory among international students in higher education. It also seeks to explore the integration of these two approaches to design adaptive learning environments. The study adopts a descriptive-analytical approach to develop an instructional framework that integrates both conceptual and practical dimensions for the development of the proposed model.

The findings reveal that the systematic integration between generative artificial intelligence and cognitive load theory enables the design of adaptive learning pathways that accommodate the learner’s proficiency level-through diagnosing educational needs, generating scaffolding content and activities, and providing immediate feedback-thereby contributing to enhanced learning outcomes. Furthermore, the article proposes an instructional model comprising five interconnected phases (diagnosis, cognitive load analysis, content personalization, feedback management, and adaptive assessment), providing a theoretical and practical framework for advancing Arabic language education in digital environments.