Enhancing Deep Learning and Motivation in University English Education through AI Technology: A Quasi-Experimental Study

Aims: This study explores the impact of AI-assisted learning on academic achievement and learning motivation in university English education. It aims to analyze the effectiveness of different AI-integrated learning environments in enhancing students’ engagement and performance. Study Design: A mixed-methods approach was employed, incorporating both exploratory and confirmatory quasi-experimental designs. Twenty-four students (six from each group) are selected for eye-tracking. Place and Duration of Study: The study was conducted at University in China over a period of four months. Methodology: The study involved two experimental phases. The exploratory phase analyzed students’ academic achievement and learning motivation in three groups: AI-driven cognitive learning (G group), multimedia-based AI learning (M group), and a control group (D group) using traditional methods. Academic performance data were collected through standardized tests, while motivation levels were assessed using a validated questionnaire. The confirmatory quasi-experimental phase compared the impact of AI-assisted learning in two different classroom types, utilizing academic performance assessments, eye-tracking data, and learning motivation surveys to measure cognitive engagement and learning effectiveness. Statistical analyses, including ANOVA and regression models, were applied to determine significant differences among the groups. Results: Findings indicated that the G group outperformed both the M and D groups in academic achievement, with an average score of 85.6 (SD = 4.2) compared to 78.3 (SD = 5.8) and 72.1 (SD = 7.5), respectively. Eye-tracking data revealed higher attention levels in AI-assisted learning environments. Additionally, students in AI-integrated learning environments exhibited increased motivation and engagement, as reflected in their questionnaire responses. Conclusion: AI-assisted learning significantly enhances students’ academic achievement and motivation in university English education. The results suggest that AI-driven cognitive learning environments are more effective than multimedia-based AI approaches. These findings provide valuable insights for educators and policymakers aiming to optimize AI integration in higher education. Further research is recommended to explore long-term effects and refine AI-based pedagogical strategies.