AI工具在应用型高校个性化学习中的应用与挑战：以体育学院为例

The Application and Challenges of AI Tools in Personalized Learning at Application-Oriented Universities: A Case Study of the School of Physical Education

摘要: 随着人工智能技术在教育领域的深入应用，探究AI工具在应用型高校个性化学习中的实际效能具有重要意义。本研究以某高校体育学院学生为对象，综合运用问卷调查、情感分析、LDA主题模型与结构方程模型等方法，系统分析了AI工具的应用现状与作用机制。研究发现，AI工具在基础学习任务中应用广泛且接受度高，但存在“高感知价值”与“低实际收益”的悖论。结构方程模型显示，AI工具的智能化水平并非学习效果的直接决定因素，而学生的自主学习能力起着关键调节作用。同时，数据隐私顾虑、工具与教学目标的冲突及推荐精度不足成为阻碍深度应用的主要瓶颈。基于56.45%的学生每日使用AI工具的现状，本研究构建了“AI-学生–教师”三维协同模型，提出应从增强AI情境感知能力、培养学生自主学习能力、促进教师融入AI教学流程及建立透明数据治理机制等方面突破现有应用局限，为应用型高校实现智能技术与个性化教育的深度融合提供了理论支持与实践路径。

Abstract: With the deeper application of artificial intelligence technology in the field of education, exploring the actual effectiveness of AI tools in personalized learning at application-oriented universities is of significant importance. This study, targeting students from a sports academy at a specific university, systematically analyzed the application status and mechanisms of AI tools by integrating methods such as questionnaires, sentiment analysis, LDA topic modeling, and structural equation modeling. The findings reveal that while AI tools are widely used and highly accepted for basic learning tasks, a paradox exists between “high perceived value” and “low actual benefits”. Structural equation modeling indicates that the intelligence level of AI tools is not a direct determinant of learning outcomes; instead, students’ self-directed learning ability plays a critical moderating role. Additionally, data privacy concerns, conflicts between AI tools and teaching objectives, and insufficient recommendation accuracy were identified as major bottlenecks hindering deeper application. Based on the observation that 56.45% of students use AI tools daily, this study constructs a tripartite collaborative model involving “AI, students, and teachers”. It proposes strategies to overcome current application limitations, such as enhancing AI’s contextual awareness, fostering students’ self-directed learning capabilities, promoting teacher integration into the AI-driven teaching cycle process, and establishing transparent data governance mechanisms. This research provides theoretical support and practical pathways for achieving deeper integration of intelligent technology and personalized education in application-oriented universities.