Mining and predicting college students behaviors from fine-grained spatial-temporal campus activity data play key roles in the academic success and personal development of college students. Most of the existing behavior prediction methods use shallow learning algorithms such as statistics, clustering, and correlation analysis approaches, which fail to mine the long-term spatial-temporal dependencies and semantic correlations from these fine-grained campus data. We propose a novel multi-fragment dynamic semantic spatial-temporal graph convolution network, named the MFDS-STGCN, on the basis of a spatial-temporal graph convolutional network (STGCN) for the automatic prediction of college students' behaviors and abnormal behaviors. We construct a dataset including 7.6 million behavioral records derived from approximately 400 students over 140 days to evaluate the effectiveness of the prediction model. Extensive experimental results demonstrate that the proposed method outperforms multiple baseline prediction methods in terms of student behavior prediction and abnormal behavior prediction, with accuracies of 92.60% and 90.84%, respectively. To further enable behavior prediction, we establish an early warning management mechanism. Based on the predictions and analyses of Big Data, education administrators can detect undesirable abnormal behaviors in time and thus implement effective interventions to better guide students' campus lives, ultimately helping them to more effectively develop and grow.

Digital maps have become important teaching and learning tools in education. However, limited research has examined the factors influencing learners’ acceptance of map-based online learning systems. This study proposes and validates an extended Technology Acceptance Model (TAM) that integrates two psychological constructs—habit and self-efficacy—into the original TAM framework to better explain students’ behavioural intention to use a map-based online learning system (Map-OLS). Structural equation modelling (SEM) was employed to analyse data from 812 participants with prior online learning experience. The results indicated that perceived ease of use (PEoU) and perceived usefulness (PU) had direct positive effects on the behavioural intention to use Map-OLS. PEoU positively affected PU and indirectly influenced behavioural intention to use Map-OLS via PU. Both habit and self-efficacy had significantly positive influences on PEoU and PU. Self-efficacy also directly influenced the behavioural intention to use Map-OLS. This study makes a theoretical contribution by extending and empirically validating TAM in the context of map-based learning environments, while also offering practical insights for designing more engaging and effective online learning systems.