Xiong Xiao

Background: ChatGPT, an AI‐based chatbot, supports learning by accurately interpreting and responding to user inputs. Despite its potential, few empirical studies have examined its influence on college students' mathematical problem‐solving processes.Objectives: This study aimed to introduce a ChatGPT‐facilitated scaffolding to investigate its impact on students' mathematical problem‐solving behaviours, performance and perceptions.Methods: Twenty‐nine undergraduates participated in this study, engaging in mathematical problem‐solving tasks using the scaffolding. A mixed‐method approach was employed, incorporating performance data, interaction analysis and self‐reported surveys to assess both quantitative and qualitative aspects of students' experiences. In particular, lag sequential analysis was applied to explore the undergraduates' problem‐solving behavioural patterns.Results and Conclusions: Results demonstrated that the ChatGPT‐facilitated scaffolding significantly improved students' mathematical problem‐solving performance. The high‐performance group (HPG) exhibited a greater frequency of interpretive and evaluative activities, transitioning from factual to metacognitive representations, while the low‐performance group (LPG) primarily transitioned from prompt selection to procedural representations. Additionally, most participants expressed positive perceptions of the scaffolding experience and reported an improvement in their problem‐solving skills.Major Takeaways: These findings offer valuable insights for the design and implementation of AI‐facilitated learning activities in mathematical problem‐solving contexts.

Rapid technological advancements are reshaping pedagogical expertise development, offering novel pathways to equip educators with 21st-century professional competencies. This study proposes an innovative AI-driven professional development approach and investigates its impact on student teachers' competence development. Twenty-eight third-year student teachers participated in tasks to mentor artificial intelligence (AI) learners, applying mentor-acquired knowledge and skills. Task performance and task processes were used to delineate teacher knowledge and teaching practices, respectively, while data from professional development surveys were thoroughly analyzed to gain in-depth insights into teacher perspectives. Findings reveal that AI teaching practice significantly enhanced participants' knowledge acquisition. Notably, high-performance groups (HPG) demonstrated complex mentoring patterns emphasizing procedural mentoring. Conversely, the low-performance group (LPG) preferred a more directive and factual approach, whose behavioral patterns appeared less significant. Furthermore, AI teaching practice also had a positive effect on student teachers' perspectives toward professional knowledge and AI literacy. The findings of this study contribute to the theoretical and practical understanding of integrating AI-based learning activities into teacher education.

Knowledge maps are teaching tools that can promote deeply learning and avoid knowledge loss by helping students plan learning paths. Mining potential association rules of concepts from student exercise data was a common method to construct knowledge maps automatically. While manual conditions should be set to filter the association rules future to improve the accuracy of knowledge maps, which made the construction of the knowledge map can not automatic totally. So, the study proposed a knowledge map construction method that combined knowledge tracking and association rule mining expanding with interaction frequencies based on exercise data to achieve rules cleaning automatically. The method first predicted students’ knowledge mastery sequences by a deep knowledge tracking model and discovered clustering relations to represent potential structures between concepts by fuzzy cluster analysis. Meanwhile, the method investigated association rule mining expanding with interaction frequencies to discover association rules between concepts. Finally, the clustering relations were used to filter the mined association rules automatically. To verify the effectiveness of the method, we constructed a knowledge map based on 34,350 online exercise data of 117 students in a computer programming course. Experimental results proved that the map was valid. Our implementations are available at https://github.com/xxdmw/FPGF-master.