Yue Li

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.

Identifying the cognitive state can help educators understand the evolving thought processes of learners, and it is important in promoting the development of higher-order thinking skills (HOTS). Cognitive neuroscience research identifies cognitive states by designing experimental tasks and recording electroencephalography (EEG) signals during task performance. However, most of the previous studies primarily concentrated on extracting features from individual channels in single-type tasks, ignoring the interconnection across channels. In this study, three learning activities (i.e., video watching activity, keyword extracting activity, and essay creating activity) were designed based on a revised Bloom’s taxonomy and the Interactive-Constructive-Active–Passive framework and used with 31 college students. The EEG signals were recorded when they were engaged in these activities. First, whole-brain network temporal dynamics were characterized by EEG microstate sequence analysis. Such dynamic changes rely on learning activity and corresponding functional brain systems. Subsequently, phase locking value was used to construct synchrony-based functional brain networks. The network characteristics were extracted to be inputted into different machine learning classifiers: Support Vector Machine, K-Nearest Neighbour, Random Forest, and eXtreme Gradient Boosting (XGBoost). XGBoost showed superior performance in the classification of cognitive states, with an accuracy of 88.07%. Furthermore, SHapley Additive exPlanations (SHAP) was adopted to reveal the connections between different brain regions that contributed to the classification of cognitive state. SHAP analysis reveals that the connections in the frontal, temporal, and central regions are most important for the high cognitive state. Collectively, this study may provide further evidence for educators to design cognitive-guided instructional activities to enhance learners’ HOTS.