Search

Construction of a Data-Driven Intelligent Teaching System for Inorganic and Analytical Chemistry and Research on Personalized Learning Models

Author(s)

Zhang Caiyan, Xu Taotao, Gao Wenwen

Affiliation(s)

School of Chemistry and Chemical Engineering, Yulin University, Yulin, Shaanxi, China

Abstract

This study addresses the issues of insufficient personalized learning support and delays in data-driven teaching decisions in traditional inorganic and analytical chemistry education. It focuses on the deep integration of artificial intelligence technology with chemistry teaching, conducting research on the development of intelligent teaching systems and innovations in personalized learning models. Employing an interdisciplinary approach that merges educational technology with chemistry, the study first constructs a three-layer system architecture that includes knowledge graph modeling, learning behavior analysis, and adaptive resource recommendations. This is achieved through the decomposition of chemical knowledge elements and relationship modeling, resulting in a dynamic knowledge graph encompassing 6 major knowledge modules and 287 core knowledge points. A student ability diagnostic model is developed based on machine learning algorithms to facilitate multidimensional analysis of learning trajectory data. Additionally, an adaptive recommendation strategy integrating cognitive diagnosis and the Zone of Proximal Development theory is designed to establish a closed-loop learning mechanism of "assessment—recommendation—feedback." Throughout the research process, educational data mining techniques are utilized to model the interaction data of over 1200 learners, verifying the system's effectiveness in supporting personalized learning. Structural equation modeling is also employed to analyze the pathway of interaction among various elements of the learning model. Empirical results indicate that this intelligent teaching system can enhance students' knowledge acquisition efficiency by 23.7% and achieve an accuracy rate of 89.2% in personalized resource matching, significantly fostering learners' ability development in understanding chemical principles and transferring experimental skills. The "technology-enabled—data-driven—dynamic adaptation" three-dimensional model constructed in this study provides a reusable methodological framework for the development of intelligent teaching systems for chemistry courses, promoting the transformation of foundational chemistry education in higher education from experience-driven to precision-focused and intelligent.

Keywords

Intelligent Teaching System; Personalized Learning Model; Knowledge Graph; Adaptive Algorithms; Educational Data Mining

References

[1] Zhu WG, Ma XF, Tian Y, Liu HJ, Lu FL, Ma YL. Construction and Application of Informationized Teaching Resources for "Inorganic Chemistry and Chemical Analysis" Based on Knowledge Graphs[J]. University Chemistry, 2024, 39(8): 113-122. [2] Wang XH, Yin XQ, Zhu L. Construction of Knowledge Graphs and Application of AI Toolkits in Smart Inorganic Chemistry Courses[J]. Chinese Journal of Chemical Education, 2024, 45(6): 42-48. [3] Zhang XW, Li H, Wang Q. Exploration on the Application of Artificial Intelligence Technology in Inorganic Chemistry Laboratory Teaching[J]. Higher Education in Chemical Engineering, 2023, 40(4): 65-71. [4] Zhou CZ, Xie ZJ. Preliminary Application of Artificial Intelligence Prediction Models in Organic Chemistry Laboratory Teaching[J]. University Chemistry, 2025, 40(2): 320-326. [5] Chen LH, Chen FF, Fan HM, Li Y, He Y. Exploration on Intelligent Teaching of Analytical Chemistry Based on Knowledge Graphs[J]. University Chemistry, 2025, 40(4): 12-18. [6] Shan LW, Yu RJ, Pu L, Wang WJ, Yu Y, Gong N. Blended Teaching Practice of Inorganic and Analytical Chemistry Experiments Focusing on Basic Scientific Literacy[J]. University Chemistry, 2021, 36(12): 200-207. [7] Teaching Team of Chemistry, Shaanxi Normal University. Practice of Reconstructing CO₂ Teaching Units through Intelligent Educational Technology Collaboration[J]. University Chemistry, 2025, 40(4): 1-7. [8] Jiang SN, Geng C. AI-Driven Construction of Personalized Knowledge Graphs and Teaching Innovation in Inorganic Chemistry[J]. Chinese Journal of Chemical Education, 2025, 46(4): 25-31.