Enhancing college Chinese learning through personalized learning paths and adaptive teaching feedback: a big data perspective

• Published in: Proceedings of SPIE, the international society for optical engineering Vol. 13682; pp. 136822Y - 136822Y-9
• Main Author: Yuan, Fang
• Format: Conference Proceeding
• Language: English
• Published: SPIE 18.06.2025
• ISBN: 1510693106; 9781510693104
• ISSN: 0277-786X
• DOI: 10.1117/12.3075584

The integration of artificial intelligence (AI) into education has the potential to revolutionize traditional teaching methods by enabling personalized learning experiences and adaptive feedback mechanisms. This study focuses on the application of AI technologies, including natural language processing (NLP) and machine learning (ML), to address the challenges of teaching college Chinese, a subject often constrained by standardized curricula and static feedback methods. The proposed framework leverages multimodal data processing to analyze student behavior, identify learning gaps, and recommend individualized learning paths. Real-time adaptive feedback, powered by sentiment analysis and reinforcement learning, ensures that instructional strategies dynamically respond to students’ performance and emotional states. The system architecture consists of three core modules: a data processing module, a learning pathway recommendation module, and an adaptive feedback module. Performance evaluation demonstrates significant improvements in student engagement and learning outcomes, with the framework achieving high accuracy in sentiment analysis (88.7%) and pathway optimization (92.4%). A case study involving 200 university students revealed a 25% improvement in test scores and engagement levels compared to traditional methods. This research highlights the transformative potential of AI in humanities education, providing a data-driven approach to bridging the gap between standardized instruction and personalized learning. Future work will explore interdisciplinary applications and address challenges related to data privacy, scalability, and algorithmic transparency.