Where it is used
Each entry identifies the volume, edition, chapter or appendix in which the work appears.
The evidence behind the series
Follow the research.
Explore every source.
Browse the scientific research and professional literature used across all seven volumes of The Science of Learning for Educators.
7book volumes
8author ranges
1searchable library
Search the collection
Find a paper, author or idea.
Choose an author range, search a title or concept, or narrow the collection by source type. Open any result to see where it appears in the books, read its evidence summary and follow available source links.
2 references
-
- Vol 4 RE: Chapter 6
self-regulated learningmultimodal dataartificial intelligencetemporal process analysisaffective measurementconstruct validityprivacy in learning analyticsJournal article Evidence summaryAt a glance
De Mooij and colleagues systematically review how multimodal data and artificial intelligence have been used to study self-regulated learning. They map studies onto a grid connecting cognitive, affective, metacognitive, and motivational processes with behavioural, contextual, physiological, and other data streams.
Key ideas
The review distinguishes unimodal, horizontal, vertical, and integrated analytic approaches and examines whether methods capture regulation as a temporal and sequential process across learning contexts. Research is moving beyond single self-report measures toward combinations such as log data, gaze, discourse, facial or physiological signals, and performance evidence. However, motivation and affect remain underrepresented, studies define and align modalities inconsistently, and conventional statistics are often used even when integrated temporal analysis is needed. AI offers possibilities for pattern detection but does not remove problems of construct validity, interpretation, privacy, or context.
Why it matters
The authors call for theoretically grounded measurement, transparent alignment of indicators with processes, stronger validation, and interdisciplinary designs that connect rich sensing with educationally meaningful support.
-
- Vol 4 RE: Chapter 18
generative artificial intelligenceself-regulated learningutility valuecognitive strategiesstudent engagementphysics instructionenglish instructionteacher oversightJournal article Evidence summaryAt a glance
Fütterer and colleagues test whether customised generative-AI support can strengthen self-regulated learning in regular secondary classrooms. In a randomized trial, 371 students in grades seven to nine completed six physics or English sessions in one of three conditions: a CustomGPT targeting utility value, a CustomGPT prompting cognitive learning strategies, or standard ChatGPT.
Key ideas
The utility-value condition produced a more favourable change in perceived usefulness than the cognitive-strategy condition. Neither tailored intervention showed clear advantages over the control for effort, domain knowledge, or elaboration-based strategy use. Exploratory analyses suggested that more meaningful engagement with the AI was associated with better-maintained interest, and effects did not differ clearly by subject. The findings provide limited, differentiated evidence rather than showing that generic AI automatically improves self-regulation.
Why it matters
Carefully designed prompts may support motivation, but strategic behaviour and learning outcomes require stronger instructional integration, reliable measures, and teacher oversight. The supplied citation calls this work a systematic review; the verified publication is an open-access randomized controlled trial.
A transparent research trail
More than a bibliography.
What it contributes
Evidence summaries explain the central idea and why the source matters to educators.
How to access it
Entries link to lawful full text where available, or to a publisher, library or purchase page.
Edition abbreviations
- TE
- Teacher Edition
- PE
- Practice Edition
- RE
- Research Edition
Citation checks
References are checked against publisher records, scholarly indexes, DOI or ISBN metadata, repositories and author records where available. An entry marked [Citation not verified] preserves the wording found in the relevant volume without attributing findings to an unconfirmed work.
From sources to a coherent pathway