Search

The level of difficulty of mathematical test items is a critical aspect for evaluating test quality and educational outcomes. Accurately predicting item difficulty during test creation is thus significantly important for producing effective test papers. This study used more than ten years of content and score data from China's Henan Provincial College Entrance Examination in Mathematics as an evaluation criterion for test difficulty, and all data were obtained from the Henan Provincial Department of Education. Based on the framework established by the National Center for Education Statistics (NCES) for test item assessment methodology, this paper proposes a new framework containing eight features considering the uniqueness of mathematics. Next, this paper proposes an XGBoost-based SHAP model for analyzing the difficulty of mathematics tests. By coupling the XGBoost method with the SHAP method, the model not only evaluates the difficulty of mathematics tests but also analyzes the contribution of specific features to item difficulty, thereby increasing transparency and mitigating the "black box" nature of machine learning models. The model has a high prediction accuracy of 0.99 for the training set and 0.806 for the test set. With the model, we found that parameter-level features and reasoning-level features are significant factors influencing the difficulty of subjective items in the exam. In addition, we divided senior secondary mathematics knowledge into nine units based on Chinese curriculum standards and found significant differences in the distribution of the eight features across these different knowledge units, which can help teachers place different emphasis on different units during the teaching process. In summary, our proposed approach significantly improves the accuracy of item difficulty prediction, which is crucial for intelligent educational applications such as knowledge tracking, automatic test item generation, and intelligent paper generation. These results provide tools that are better aligned with and responsive to students' learning needs, thus effectively informing educational practice. [ABSTRACT FROM AUTHOR]

Background and aim: Driven by Innovation 2.0 (the information age, the innovation form of the knowledge society), the form evolved by the Internet development, giving rise to economic and social development ("Internet +"). With this background, a novel approach is presented for fostering excellence in physicians, aligning with the contemporary demands of our era. Methods: Self-administered questionnaire was used to facilitate the collection of data on medical advanced mathematics course offerings, distribution of teaching hours of each major and the perception of the course teaching system in 11 medical universities in China. The distribution of course offerings in each major was analyzed, and one-sample t-test was conducted on the perspectives of course offerings, content settings (theoretical & practical), educational objectives, teaching reforms, and Synthetical Sensation (SS) of the curriculum system and educational model. Results: The study included various specialties such as clinical medicine, pharmacy, public health, health management, and life sciences, all of which offered advanced mathematics course. The content of medical mathematics textbooks was designed to meet the practical needs of relevant professions, and encompass online laboratory classes and social practice. However, a noticeable misalignment was observed between the content of medical mathematics courses and the realistic requirements of professions (t = -3.614~-3.018, P < 0.05). The perceived difference in the completeness of curriculum systems was not significantly apparent. There was a difference in the perception of the effectiveness of teaching reforms (t = -4.485, P < 0.05), and there was a difference in the perception of the synthesis of the educational model in all cases (t = -5.067, P < 0.05). Conclusion: There are localized differences in curricula, and the number of course hours is basically reasonable; course content needs to be updated; the implementation of course objectives is not in place; the curriculum system can meet the needs of talent training; the innovation of the education model needs to be put into practice; and there are obvious differences in the comprehensive cognition of the teaching system and the education model. Based on the analysis of the problems, we build a new STC teaching mode with smart classroom based on "professional needs, practical needs and requirements for cultivating excellent physician talents". [ABSTRACT FROM AUTHOR]