Multimodal data collection is increasingly common but analyses rarely align data streams temporally¶

Claim · All claims
Evidence · 1 study · review r3 · q2
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Although integrated data collection is growing, studies mostly analyse streams sequentially rather than aligning their temporality as the parallel method requires. → Susanne de Mooij 2025

Evidence¶

Susanne de Mooij 2025¶

Susanne de Mooij, Joni Lämsä, Lyn Lim, Olli Aksela, Shruti Athavale, Inti Bistolfi, Flora Jin, Tongguang Li, Roger Azevedo, Maria Bannert, Dragan Gašević, Sanna Järvelä, Inge Molenaar. (2025). A Systematic Review of Self-Regulated Learning through Integration of Multimodal Data and Artificial Intelligence. Educational Psychology Review. https://doi.org/10.1007/s10648-025-10028-0

q2 · i? · review · r3

The review's analysis of analytical methods (RQ3) found that even in integrated approaches, studies often examine processes and modalities sequentially rather than synchronising data streams. It reports that "Aligning data streams is much more challenging to do and was rarely found in our review."

"Studies focus more on individual processes and employ a sequential method of analysis instead of trying to align the temporality of data streams well to capture the dynamic relationship between data streams and modalities, in line with the parallel method."

Discussion¶

Related Claims¶

• Metacognition assessment is shifting from self-report questionnaires toward process-oriented multimodal methods, which face validity and data-alignment challenges — possibly the same claim (merge candidate)
• T-pattern analysis detected temporal-structure differences between children with specific language disorder and typically developing children that frequency and sequential lag analyses did not — related
• Mind wandering can both prompt SRL and function as a regulatory strategy, and multimodal machine-learning sensing offers scalable assessment of attentive states — related
• Lag-sequential Analysis reveals temporal ordering patterns in CSCL interaction that traditional coding-and-counting approaches hide — related
• Epistemic network analysis provides a better account of temporal patterns between socio-cognitive events than coding-and-counting — related