Rethinking MMLA: Design Considerations for Multimodal Learning Analytics Systems
Published in Proceedings of the Tenth ACM Conference on Learning @ Scale, 2023
This paper explores the complexities of designing Multimodal Learning Analytics (MMLA) systems by identifying key considerations critical to their development. These considerations include data management, human factors, sensors and modalities, learning scenarios, privacy and ethics, interpretation and feedback, and data collection. The study emphasizes two main implications: the need for flexibility in MMLA systems to accommodate diverse learning contexts and scales, and the importance of a researcher-centered approach in their design. Recognizing the potential for “analysis paralysis” due to the numerous factors involved, this paper encourages researchers to rethink MMLA design and offers valuable guidance for developers and practitioners in the field.