Challenges and opportunities of multimodal data in human learning: The computer science students' perspective

• Published in: Journal of computer assisted learning Vol. 37; no. 4; pp. 1030 - 1047
• Main Authors: Mangaroska, Katerina, Martinez‐Maldonado, Roberto, Vesin, Boban, Gašević, Dragan
• Format: Journal Article
• Language: English
• Published: Chichester, UK John Wiley & Sons, Inc 01.08.2021; Wiley; Wiley Subscription Services, Inc
• Subjects: Authentic Learning; Computer science; Computer Science Education; Context; Designers; Education; Educational technology; Ethics; Guidelines; higher education; human‐centred analytics; Learning; Learning Analytics; Learning Modalities; Measurement Equipment; multimodal learning analytics; pervasive surveillance; privacy; Qualitative analysis; Student Attitudes; Students; thematic analysis
• ISSN: 0266-4909; 1365-2729
• DOI: 10.1111/jcal.12542

Multimodal data have the potential to explore emerging learning practices that extend human cognitive capacities. A critical issue stretching in many multimodal learning analytics (MLA) systems and studies is the current focus aimed at supporting researchers to model learner behaviours, rather than directly supporting learners. Moreover, many MLA systems are designed and deployed without learners' involvement. We argue that in order to create MLA interfaces that directly support learning, we need to gain an expanded understanding of how multimodal data can support learners' authentic needs. We present a qualitative study in which 40 computer science students were tracked in an authentic learning activity using wearable and static sensors. Our findings outline learners' curated representations about multimodal data and the non‐technical challenges in using these data in their learning practice. The paper discusses 10 dimensions that can serve as guidelines for researchers and designers to create effective and ethically aware student‐facing MLA innovations. Lay Description What is already known about this topic Many MLA systems are designed without learners' involvement. Understanding of how multimodal data can support learners' authentic needs is needed. MLA have the potential to enable the automated generation of models to provide real‐time feedback. What this paper adds Understanding how learners perceive multimodal data and the learning context. The findings outline the soft challenges in using multimodal data in the learning practice. Ten dimensions were identified to serve as guidelines for researchers and designers. The paper reports learners' perspectives describing new, intriguing, and under‐developed ideas about potential uses of multimodal data in educational context. The discussion on the need for human‐centred design approaches for educational technologies has been presented. Implications for practice and/or policy Relevant pointers for what is appropriate and ethically necessary when designing learning technologies. Change in perspective among educators, on how they address progress and engagement in learning.