Dissecting the Temporal Dynamics of Embodied Collaborative Learning Using Multimodal Learning Analytics

Embodied collaborative learning, intertwining verbal and physical behaviors, is an intricate learning process demanding a multifaceted approach for comprehensive understanding. Prior studies in this field have often neglected the temporal dynamics and the interplay between verbal and bodily behaviors in collaborative learning settings. This study bridges this gap by employing an integrative approach combining social constructivism, situated cognition, and embodied cognition theories through multimodal learning analytics (MMLA) to dissect the temporal dynamics of embodied collaborative learning in a simulated clinical setting. The study operationalized the linguistic, contextual, and bodily elements of each theoretical perspective, focusing on analyzing the verbal communication, spatial behavior, and physiological responses of 56 students across 14 sessions. These multimodal data were analyzed using correlation analysis and epistemic network analysis. The results illustrated the interconnected nature of students' verbal communication and spatial behaviors during collaborative learning and demonstrated that an MMLA approach could effectively capture the temporal dynamics of these behaviors across different learning phases. The study also identified significant differences in the behaviors of efficient and inefficient teams and between satisfied and dissatisfied students, primarily linked to spatial behaviors. These insights underline the utility of MMLA in providing a nuanced understanding of collaborative learning behavior from an integrated theoretical perspective, with implications for learning design and the development of reflection and in-the-moment analytics. This study sets the stage for further exploration of the multifaceted dynamics of collaborative learning, underscoring the value of a multimodal approach to learning analytics and educational research. Educational Impact and Implications Statement This study enhances our understanding of embodied collaborative learning in clinical simulations by integrating social constructivism, situated cognition, and embodied cognition theories. Utilizing multimodal learning analytics (MMLA), it reveals how students' verbal, spatial, and physiological behaviors intricately interact during learning processes. The findings highlight the potential of MMLA in supporting feedback and reflection practices by identifying key behavioral differences in collaborative environments.