Dataset of coded articles as part of 'A systematic review of self-regulated learning through integration of multimodal data and artificial intelligence'

This dataset represents the included papers from a systematic review called 'A systematic review of self-regulated learning through integration of multimodal data and artificial intelligence', published in the journal Educational Psychology Review DOI: 10.1007/s10648-025-10028-0 We used three databases (ERIC, Scopus, Web of Science) to identify peer-reviewed empirical journal articles and proceedings published in English. All searches were conducted between November 2022 and January 2023 with search terms referring to (a) self-regulated learning, (b) multimodal data, and (c) analytics. The dataset includes the title, journal, and publication year of the paper. Then, with a team of 8 coders, we have labelled the following as best as possible: CAMMprocess = which CAMM processes (i.e., cognition, metacognition, affective state, motivation) were diagnosed Datastream = Datastreams used to measure these CAMM processes AnalyticalApproach = The approaches (unimodal, horizontal, vertical, or integrated) were coded for each study by calculating the number of CAMM processes measured as well as the number of data streams used. Analysis = The analytical methods were coded and categorised into qualitative analysis, clustering, Markov modelling, process mining, standard statistics, (lag) sequential analysis (lag seq. analysis), network analysis, decision trees, Support Vector Machine (SVM), Natural Language Processing (NLP), Recurrence Quantification Analysis (RQA), and discourse analysis. Sample size = Number of participants EducationalLevel = Educational level of the participants (i.e., primary, secondary, or higher education) LearningIndividual = individual or collaborative learning settings LearningEnvironment = whether conducted in authentic or laboratory learning environments NumberSessions = data collected in one single session or across multiple sessions DataCategory = Category of data stream (i.e., behavioural, contextual, and physiological data) SRLTheory = SRL theories mentioned that were used as basis For more details on how these codes were defined, please read the article in Educational Psychology Review. As a team we have done our best to provide the correct labels, but we welcome especially the authors of the papers to provide feedback and/or revisions to this dataset. Additions to this paper are also welcome. This can be send to email address: [e-mail]