Navigating anxiety in digital learning: How AI-driven personalization and emotion recognition shape EFL students'...

As artificial intelligence (AI) technologies become increasingly integrated into educational contexts, understanding their influence on learners' emotional and cognitive engagement is essential. This study investigates the relationship between AI-driven personalization, emotion recognition, digital learning anxiety, and student engagement among Chinese university students learning English as a Foreign Language (EFL). Data were collected via an online questionnaire administered between April 21st and April 30th, yielding a valid sample of 493 participants. The instruments were translated and back-translated to ensure linguistic and cultural validity. Using SPSS (version 27) and AMOS (version 24), both correlation and structural equation modeling analyses were conducted. Results showed that AI-driven personalization and emotion recognition were positively correlated with engagement and negatively correlated with digital learning anxiety. Furthermore, mediation analysis indicated that anxiety partially mediated the relationship between AI technologies and engagement. The structural model demonstrated strong fit indices, highlighting the efficacy of AI-based tools in reducing anxiety and enhancing student engagement. These findings underscore the theoretical relevance of the Control-Value Theory and Engagement Theory and offer practical insights for the implementation of emotionally responsive AI systems in EFL digital learning environments.