Use multimodal data and time-sensitive analyses to capture situational motivational processes¶

Strategy · All strategies
Evidence · 3 claims (3 for) · 1 study (1 review), q3 · 0 of 1 report an effect size · 3 claims rest on one study

Description¶

The review recommends that future research and learning-technology design exploit multimodal data sources — such as physiological measures, log data, and wearable-device tracking correlated with self-reports — together with time-sensitive analyses, to capture moment-to-moment motivational fluctuation in authentic learning. The authors state: "Future research should explore the potential of multimodal data and the more extensive use of time-sensitive analyses to capture the complexity and developmental aspects of motivational processes." This knowledge is intended to inform personalized AI-based support systems that respond in the moment to students' motivational needs as part of self-regulated learning.

Design Implications¶

Context¶

Requirements¶

• Online measures capturing real-time fluctuation with varying granularity (e.g., ESM, physiological data, log-data) combined with self-reports of subjective motivational interpretations

Constraints¶

• The review found only 19% (n = 15) of existing studies used an additional complementary data channel, and motivation has been underemphasized in SRL research using unobtrusive multimodal data

Target Learners¶

• Students in academic learning contexts, including adults, adolescents, and children

Target Learning Goals¶

• Supporting students' motivation in real time as part of self-regulated learning, including planning, monitoring, and controlling learning processes

Claims¶

• Interconnections between motivational constructs and learning are complex and temporal, evidenced by 78% (n = 14) of momentary-wave studies [+W]
• During an exam, students' expectancy for success decreased and the change in expectancy was negatively associated with change in salivary cortisol [+W]
• Situational motivation is influenced by the learning context, with evidence mainly from situation-specific studies (65%) rather than momentary studies (28%) [+W]

Related Strategies¶

• Use multimodal data channels combining subjective and objective measures to overcome single-channel constraints in SSRL research
• Triangulate physiological data with other CSCL data streams ( such as video or logfile traces ) to uncover otherwise unidentifiable psychophysiological reactions
• Combine log-derived behavioral engagement measures with process data and self-report to assess learner engagement in AI-supported practice
• Study effort regulation in real-world, personally relevant contexts over longer timeframes, including via ecological momentary assessment
• Use automated mind-wandering detection in attention-aware learning technologies to trigger real-time interventions that promote SRL strategies
• Future team-learning change research should use mixed methods with more than three measurement points in short intervals
• Supplement self-report questionnaires with process-oriented and online measures of motivation during learning
• Model assets and threats to availability by blending inter-individual self-reports with process-oriented intraindividual online measures
• Employ multimodal methods to capture the multifaceted feedback process

Examples¶

-

Key Sources¶

• Törmänen, T., Ketonen, E., Lehtoaho, E., Turunen, M., Zabolotna, K., Shubina, T., & Järvenoja, H. (2025). Situational Motivation in Academic Learning: A Systematic Review. Educational Psychology Review. https://doi.org/10.1007/s10648-025-10036-0