Problem-based learning (PBL) has been used in different domains, and there is overwhelming evidence of its value. As an emerging field with excellent prospects, learning analytics (LA)—especially multimodal learning analytics (MMLA)—has increasingly attracted the attention of researchers in PBL. However, current research on the integration of LA with PBL has not related LA results with specific PBL steps or paid enough attention to the interaction in peer learning, especially for text data generated from peer interaction. This study employed MMLA based on machine learning (ML) to quantify the process engagement of peer learning, identify log behaviors, self-regulation, and other factors, and then predict online PBL performance. Participants were 104 fourth-year students in an online course on social work and problem-solving. The MMLA model contained multimodal data from online discussions, log files, reports, and questionnaires. ML classification models were built to classify text data in online discussions. The results showed that self-regulation, messages post, message words, and peer learning engagement in representation, solution, and evaluation were predictive of online PBL performance. Hierarchical linear regression analyses indicated stronger predictive validity of the process indicators on online PBL performance than other indicators. This study addressed the scarcity of students’ process data and the inefficiency of analyzing text data, as well as providing information on targeted learning strategies to scaffold students in online PBL.

The emergency response ability of police officers is a critical component of their career, and is also an important support for public security. However, few researchers have focused on the factors that influence emergency response ability, especially in the group of novice policemen. On the other hand, as the popular way to train emergency response ability, case-based instruction (CBI) generates various types of data, especially valuable text data; however, such text data is always ignored because of the lack of effective analysis methods. Therefore, this study employed automatic semantic analysis and hierarchical linear regression models to investigate the factors influencing the emergency response ability of novice policemen in the process of CBI. Results indicated that, among personal differences, prior knowledge, and basic professional skills, the latter showed stronger predictive validity than the others. In particular, information processing and judgment, command and decision, and order maintenance were the main indicators. This study also illustrated that automatic semantic analysis can effectively identify deep value from semantic data, which will support stakeholders to design strategies, make decisions, conduct evaluations in training and instructions, and ultimately help sustainable development in human careers.

No abstract

No abstract

No abstract