Use multimodal data channels combining subjective and objective measures to overcome single-channel constraints in SSRL research¶

Strategy · All strategies
Evidence · no claims cited

Description¶

The review's stated forward methodological path is to widen data channels toward multimodal data, combining subjective measures (self-reports, interviews) that capture intent and appraisal with objective data (log data, eye tracking, heart rate, electro-dermal activity, videos, facial expressions). It states that multimodal approaches "can help tackle the constraints of typical single-channel data" and help draw "more valid and reliable inferences". In CSCL practice, it argues participants would benefit from tools helping groups regulate learning within the groups.

Design Implications¶

Context¶

Requirements¶

• Methods able to align multimodal data streams that come with different sampling rates
• More evidence on what modalities such as electrodermal activity and heart rate reveal about learning and collaboration

Constraints¶

• Multimodal data application is still in early stages because of differing sampling rates and alignment difficulties

Target Learners¶

• students in collaborative learning groups
• CSCL researchers

Target Learning Goals¶

• understanding and supporting regulation of cognition, motivation, and emotion in collaboration

Related Strategies¶

• Broaden co-regulation methodology using trace data, server logs, episodic coding and multilevel modelling
• Triangulate physiological data with other CSCL data streams ( such as video or logfile traces ) to uncover otherwise unidentifiable psychophysiological reactions
• Use multimodal data and time-sensitive analyses to capture situational motivational processes
• Integrate physiological, dialog, video, and self-report data to analyze collaboration at individual and group levels
• Research agenda: investigate affective dynamics with within-person, longitudinal, and multi-channel methods
• Adopt an integrative methodological toolkit using machine learning and computational models to capture SR's multi-level, temporal, and social dynamics
• Employ multimodal methods to capture the multifaceted feedback process

Examples¶

-

Key Sources¶

• Järvelä, S., Järvenoja, H., & Malmberg, J. (2019). Capturing the dynamic and cyclical nature of regulation: Methodological Progress in understanding socially shared regulation in learning. International Journal of Computer-Supported Collaborative Learning. https://doi.org/10.1007/s11412-019-09313-2