pith. machine review for the scientific record. sign in

arxiv: 2605.14228 · v1 · submitted 2026-05-14 · 💻 cs.HC · cs.LG

Recognition: no theorem link

Self-Regulated Learning in Essay Writing: Consistency of Strategies and Impact on Outcomes

Gloria Fern\'andez-Nieto , Kiyoshige Garc\'es , Mladen Rakovi\'c , Tongguang Li , Xinyu Li , Linxuan Zhao , Dragan Ga\v{s}evi\'c
Authors on Pith no claims yet

Pith reviewed 2026-05-15 02:36 UTC · model grok-4.3

classification 💻 cs.HC cs.LG
keywords self-regulated learningSRL strategiesonline essay writingtrace dataprocess miningsecondary schoollearning outcomesstrategy variability
0
0 comments X

The pith

Secondary school students show three main SRL strategies in online essay writing, with variability across sessions and one linked to better outcomes.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This study examines how secondary school students use self-regulated learning strategies during online essay writing tasks and how those strategies change from one session to the next. By collecting metacognition-related trace data from nearly 100 students in two Colombian schools across two sessions one week apart, the authors apply process mining and machine learning to uncover patterns. The work shows that strategies are not fixed, as many students stick with or move toward reading first then writing, while a strategy of writing intensively with selective reading vanishes in the second session but correlates with stronger outcomes when used. Understanding these patterns matters because it can guide the creation of digital tools that support effective learning habits in online environments during adolescence.

Core claim

The central discovery is that three dominant SRL strategies were identified from the trace data. Strategies showed variability: many students remained in or shifted to Read first, write next, while none used Write intensively, read selectively in session 2. Although less common, the latter strategy was positively associated with learning outcomes.

What carries the argument

Process mining and unsupervised machine learning techniques applied to metacognition-related trace data from a digital learning platform to identify dominant SRL strategies.

If this is right

  • Many students remain in or shift to a read first, write next strategy across the two sessions.
  • None of the students used the write intensively, read selectively strategy in the second session.
  • The write intensively, read selectively strategy is positively associated with learning outcomes.
  • SRL strategies exhibit variability over time rather than remaining consistent.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Digital platforms could incorporate real-time monitoring of SRL strategies to offer timely support.
  • Interventions aimed at promoting the effective strategy could be tested in similar online settings.
  • These patterns may inform broader designs for online education tools targeting adolescent learners.

Load-bearing premise

The logged trace data from the digital platform accurately and comprehensively captures students' metacognitive SRL processes without substantial measurement error, missing actions, or platform-specific biases.

What would settle it

A study using direct observation or different data collection methods that finds different strategy clusters or no association with outcomes would falsify the results.

Figures

Figures reproduced from arXiv: 2605.14228 by Dragan Ga\v{s}evi\'c, Gloria Fern\'andez-Nieto, Kiyoshige Garc\'es, Linxuan Zhao, Mladen Rakovi\'c, Tongguang Li, Xinyu Li.

Figure 1
Figure 1. Figure 1: Screenshot of the multi-source writing task and the learning environment. [PITH_FULL_IMAGE:figures/full_fig_p005_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Process from students’ trace data to SRL strategies. [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Three SRL strategies were identified using the First-Order Markov Model (FOMM) and Expectation [PITH_FULL_IMAGE:figures/full_fig_p008_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Sankey diagram showing students’ transitions between SRL strategies from Session 1 to Session 2. [PITH_FULL_IMAGE:figures/full_fig_p010_4.png] view at source ↗
read the original abstract

Background: Abilities for effective self-regulated learning (SRL) are critical for lifelong learning, particularly during adolescence when these skills consolidate and strongly influence future learning. Their importance has grown with the rise of online and blended education. Yet, little is known about how secondary school students self-regulate in online environments, how their SRL processes and strategies evolve, or how they affect outcomes. In secondary education, understanding these processes can reveal patterns and indicators of learning success, informing the design of online support mechanisms. Evidence from repeated-measures designs remains scarce. Objectives: This study aims to examine how secondary school students enact SRL strategies during online essay writing, how these strategies change over time, and how they relate to learning outcomes. Methods: We analysed metacognition-related trace data collected from secondary students during a two-wave online essay-writing task conducted one week apart in two Colombian schools (N = 93 for session 1, N = 95 for session 2) via a digital learning platform. Using a combination of process mining and unsupervised machine learning techniques, we identified dominant SRL strategies grounded in established SRL processes and examined their stability and association with learning outcomes. Results and conclusions: Three dominant SRL strategies were identified. Results showed variability: many students remained in or shifted to Read first, write next, while none used Write intensively, read selectively in session 2. Although less common, latter strategy was positively associated with learning outcomes.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The paper examines self-regulated learning (SRL) strategies among secondary school students in two online essay-writing sessions one week apart (N=93 and 95) using trace logs from a digital platform. It combines process mining and unsupervised machine learning to identify three dominant SRL strategies, assesses their stability and shifts over time, and reports that one less-common strategy (Write intensively, read selectively) is positively associated with learning outcomes while many students remain in or shift to Read first, write next.

Significance. If the logged actions validly encode metacognitive SRL processes, the work provides rare repeated-measures evidence on strategy consistency and outcome links in adolescent online writing, with potential to inform platform design for secondary education.

major comments (2)
  1. [Methods] Methods: The central claim that trace logs yield interpretable SRL strategies rests on unsupervised clustering without any reported external validation (think-aloud protocols, expert session coding, or correlation with self-report SRL inventories). If clusters primarily capture platform affordances rather than metacognitive processes, both the stability findings and the outcome association become uninterpretable.
  2. [Results] Results: The reported positive association between the 'Write intensively, read selectively' strategy and outcomes is presented without cluster-validation statistics (e.g., silhouette scores, cross-session stability), exact outcome metrics, or statistical controls for confounders and missing data; these omissions leave the strength and robustness of the link unverifiable.
minor comments (1)
  1. [Abstract] Abstract: High-level description of sample sizes and methods is given, but details on cluster validation, precise outcome measures, and missing-data handling are absent, reducing the reader's ability to assess the reported associations.

Simulated Author's Rebuttal

2 responses · 1 unresolved

We thank the referee for their constructive feedback on our manuscript examining SRL strategies via trace data in online essay writing. We address each major comment below, indicating planned revisions where appropriate.

read point-by-point responses

  1. Referee: [Methods] The central claim that trace logs yield interpretable SRL strategies rests on unsupervised clustering without any reported external validation (think-aloud protocols, expert session coding, or correlation with self-report SRL inventories). If clusters primarily capture platform affordances rather than metacognitive processes, both the stability findings and the outcome association become uninterpretable.

    Authors: We acknowledge that the absence of external validation (e.g., think-aloud protocols or self-report correlations) is a limitation of the current trace-only design. The clusters were derived by first applying process mining to extract sequential patterns from logged actions, then mapping those to core SRL phases (forethought, performance, reflection) drawn from established models such as Zimmerman (2002). We will revise the Methods section to provide greater detail on feature selection and the theoretical grounding of each action category. We will also add an expanded limitations discussion explicitly addressing the risk that clusters may partly reflect platform affordances and noting that future work should include concurrent validation measures. These changes clarify the interpretive basis without overstating the evidence. revision: partial

  2. Referee: [Results] The reported positive association between the 'Write intensively, read selectively' strategy and outcomes is presented without cluster-validation statistics (e.g., silhouette scores, cross-session stability), exact outcome metrics, or statistical controls for confounders and missing data; these omissions leave the strength and robustness of the link unverifiable.

    Authors: We will revise the Results section to report silhouette scores for the k-means clustering solution and quantitative measures of cross-session strategy stability (e.g., transition probabilities and Cohen’s kappa). The outcome metric is the platform-generated essay quality score (0–100 scale) based on a rubric covering content, organization, and language use. We will add multiple regression models that control for session order, school, and available baseline performance indicators, along with a description of missing-data handling (primarily listwise deletion given low rates). These additions will allow readers to assess the robustness of the reported association. revision: yes

standing simulated objections not resolved
  • We do not have access to concurrent think-aloud protocols, expert-coded sessions, or self-report SRL inventories in the existing dataset, so direct external validation of the clusters cannot be performed retrospectively.

Circularity Check

0 steps flagged

No significant circularity: empirical identification from external trace logs

full rationale

The paper applies standard process mining and unsupervised machine learning directly to logged trace data collected from secondary students on a digital platform. The three dominant SRL strategies are discovered as clusters in that data rather than defined in terms of the outcome associations or any fitted parameter that would make the target result tautological. No equations, self-definitional reductions, or load-bearing self-citations are present that collapse the reported stability findings or outcome links back to the inputs by construction. The approach remains externally falsifiable against the raw logs and is therefore self-contained.

Axiom & Free-Parameter Ledger

1 free parameters · 1 axioms · 0 invented entities

The central claims rest on the assumption that platform trace logs faithfully represent SRL processes and that unsupervised clustering yields interpretable, stable strategies; the number of clusters appears chosen to produce three dominant groups.

free parameters (1)
  • Number of clusters
    Unsupervised ML was used to identify three dominant strategies, implying k=3 was selected or validated on the trace data.
axioms (1)
  • domain assumption Trace data from the digital platform accurately reflects metacognitive SRL processes
    The study grounds strategies in established SRL processes but assumes logged actions (reading, writing sequences) capture the intended cognitive and regulatory behaviors without major gaps or distortions.

pith-pipeline@v0.9.0 · 5593 in / 1276 out tokens · 31125 ms · 2026-05-15T02:36:26.691306+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

42 extracted references · 42 canonical work pages

  1. [1]

    Zimmerman

    Barry J. Zimmerman. Self-regulated learning and academic achievement: An overview.Educational Psychologist, 25(1):3–17, 1990.https://doi.org/10.1207/s15326985ep2501_2

    work page doi:10.1207/s15326985ep2501_2 1990

  2. [2]

    Studying as self-regulated learning

    Philip H Winne and Allyson F Hadwin. Studying as self-regulated learning. InMetacognition in educational theory and practice, pages 291–318. Routledge, 1998

    work page 1998

  3. [3]

    Taylor & Francis, 2011

    Dale H Schunk and Barry Zimmerman.Handbook of self-regulation of learning and performance. Taylor & Francis, 2011

    work page 2011

  4. [4]

    Improving the measurement of self-regulated learning using multi-channel data.Metacognition and Learning, 17(3):1025–1055, 2022

    Yizhou Fan, Lyn Lim, Joep Van der Graaf, Jonathan Kilgour, Mladen Rakovi ´c, Johanna Moore, Inge Mole- naar, Maria Bannert, and Dragan Gaševi ´c. Improving the measurement of self-regulated learning using multi-channel data.Metacognition and Learning, 17(3):1025–1055, 2022. https://doi.org/10.1007/ s11409-022-09304-z

    work page 2022

  5. [5]

    A learning analytic approach to unveiling self-regulatory processes in learning tactics

    Yizhou Fan, John Saint, Shaveen Singh, Jelena Jovanovic, and Dragan Gaševi´c. A learning analytic approach to unveiling self-regulatory processes in learning tactics. InLAK21: 11th international learning analytics and knowledge conference, pages 184–195, 2021.https://doi.org/10.1145/3448139.344821

    work page doi:10.1145/3448139.344821 2021

  6. [6]

    Self-regulated learning strategies & academic achievement in online higher education learning environments: A systematic review.The Internet and Higher Education, 27:1–13, 2015

    Jaclyn Broadbent and Walter L Poon. Self-regulated learning strategies & academic achievement in online higher education learning environments: A systematic review.The Internet and Higher Education, 27:1–13, 2015. https://doi.org/10.1016/j.iheduc.2015.04.007

    work page doi:10.1016/j.iheduc.2015.04.007 2015

  7. [7]

    Effects of internal and external conditions on 13 APREPRINT- MAY15, 2026 strategies of self-regulated learning: A learning analytics study

    Namrata Srivastava, Yizhou Fan, Mladen Rakovic, Shaveen Singh, Jelena Jovanovic, Joep Van Der Graaf, Lyn Lim, Surya Surendrannair, Jonathan Kilgour, Inge Molenaar, et al. Effects of internal and external conditions on 13 APREPRINT- MAY15, 2026 strategies of self-regulated learning: A learning analytics study. InLAK22: 12th International Learning Analytics...

    work page doi:10.1145/3506860.350697 2026

  8. [9]

    Towards investigating the validity of measurement of self-regulated learning based on trace data.Metacognition and Learning, 17(3):949–987, 2022

    Yizhou Fan, Joep van der Graaf, Lyn Lim, Mladen Rakovi´c, Shaveen Singh, Jonathan Kilgour, Johanna Moore, Inge Molenaar, Maria Bannert, and Dragan Gaševi ´c. Towards investigating the validity of measurement of self-regulated learning based on trace data.Metacognition and Learning, 17(3):949–987, 2022. https://doi. org/10.1007/s11409-022-09291-1

    work page doi:10.1007/s11409-022-09291-1 2022

  9. [10]

    Roger Azevedo, Daniel C Moos, Jeffrey A Greene, Fielding I Winters, and Jennifer G Cromley. Why is externally- facilitated regulated learning more effective than self-regulated learning with hypermedia?Educational Technology Research and Development, 56:45–72, 2008.https://doi.org/10.1007/s11423-007-9067-0

    work page doi:10.1007/s11423-007-9067-0 2008

  10. [11]

    How do students learn with real-time personalized scaffolds?British Journal of Educational Technology, 55(4):1309–1327, 2024.https://doi.org/10.1111/bjet.13414

    Lyn Lim, Maria Bannert, Joep van der Graaf, Yizhou Fan, Mladen Rakovic, Shaveen Singh, Inge Molenaar, and Dragan Gaševi´c. How do students learn with real-time personalized scaffolds?British Journal of Educational Technology, 55(4):1309–1327, 2024.https://doi.org/10.1111/bjet.13414

    work page doi:10.1111/bjet.13414 2024

  11. [12]

    Sami Heikkinen, Mohammed Saqr, Jonna Malmberg, and Matti Tedre. Supporting self-regulated learning with learning analytics interventions–a systematic literature review.Education and Information Technologies, 28(3):3059–3088, 2023.https://doi.org/10.1007/s10639-022-11281-4

    work page doi:10.1007/s10639-022-11281-4 2023

  12. [13]

    Analytics of planning behaviours in self-regulated learning: Links with strategy use and prior knowledge

    Tongguang Li, Yizhou Fan, Namrata Srivastava, Zijie Zeng, Xinyu Li, Hassan Khosravi, Yi-Shan Tsai, Zachari Swiecki, and Dragan Gaševi´c. Analytics of planning behaviours in self-regulated learning: Links with strategy use and prior knowledge. InLAK24, pages 438–449, 2024.https://doi.org/10.1145/3636555.363690

    work page doi:10.1145/3636555.363690 2024

  13. [14]

    Halima Alnashiri, Mladen Rakovic, Sadia Nawaz, Xinyu Li, Joni Lämsä, Lyn Lim, Maria Bannert, Sanna Jarvela, and Dragan Gasevic. Using trace data of secondary students to understand metacognitive processes in writing from multiple sources.Journal of Computer Assisted Learning, 41, 09 2025.https://10.1111/jcal.70114

    work page doi:10.1111/jcal.70114 2025

  14. [15]

    Reinforcement learning for automatic detection of effective strategies for self-regulated learning.Computers and Education: Artificial Intelligence, 5:100181, 2023

    Ikenna Osakwe, Guanliang Chen, Yizhou Fan, Mladen Rakovic, Xinyu Li, Shaveen Singh, Inge Molenaar, Maria Bannert, and Dragan Gaševi´c. Reinforcement learning for automatic detection of effective strategies for self-regulated learning.Computers and Education: Artificial Intelligence, 5:100181, 2023. https://10.1016/ j.caeai.2023.100181

    work page arXiv 2023

  15. [16]

    Transfer Reinforcement Learning for Self-Regulated Learning Support: An Evaluation Using Successor Representations

    Kiyoshige Garces, Gloria Milena Fernandez-Nieto, Mladen Rakovic, Xinyu Li, Tongguang Li, Linxuan Zhao, Dragan Gaševi´c, Junyu Xuan, and Hua Zuo. Transfer Reinforcement Learning for Self-Regulated Learning Support: An Evaluation Using Successor Representations. InProceedings of the 26th International Conference on Artificial Intelligence in Education, page...

    work page doi:10.1007/978-3-031-98465-5_55 2025

  16. [17]

    Components of fostering self-regulated learning among students

    Charlotte Dignath and Gerhard Büttner. Components of fostering self-regulated learning among students. a meta- analysis on intervention studies at primary and secondary school level.Metacognition and learning, 3(3):231–264, 2008.https://doi.org/10.1007/s11409-008-9029-x

    work page doi:10.1007/s11409-008-9029-x 2008

  17. [18]

    Analysis of self-regulated learning skills in senior high school students: A phenomenological study.TEM Journal, 10(3), 2021

    Ameliasari Tauresia Kesuma, Heri Retnawati, and Himawan Putranta. Analysis of self-regulated learning skills in senior high school students: A phenomenological study.TEM Journal, 10(3), 2021. http://temjournal.com/ content/103/TEMJournalAugust2021_1285_1293.pdf

    work page 2021

  18. [19]

    Weil, Stephen M

    Leonora G. Weil, Stephen M. Fleming, Iroise Dumontheil, Emma J. Kilford, Rimona S. Weil, Geraint Rees, Raymond J. Dolan, and Sarah-Jayne Blakemore. The development of metacognitive ability in adolescence. Consciousness and Cognition, 22(1):264–271, March 2013.https://10.1016/j.concog.2013.01.004

    work page doi:10.1016/j.concog.2013.01.004 2013

  19. [20]

    Self-regulated learning processes in secondary education: A network analysis of trace-based measures

    Yixin Cheng, Rui Guan, Tongguang Li, Mladen Rakovi´c, Xinyu Li, Yizhou Fan, Flora Jin, Yi-Shan Tsai, Dragan Gaševi´c, and Zachari Swiecki. Self-regulated learning processes in secondary education: A network analysis of trace-based measures. InProceedings of the 15th International Learning Analytics and Knowledge Conference, pages 260–271, 2025.https://doi...

    work page doi:10.1145/3706468.3706502 2025

  20. [21]

    N. L. Higgins, Joseph A. Rathner, and Sarah Frankland. Development of self-regulated learning: a longitudinal study on academic performance in undergraduate science.Research in Science and Technological Education, 2023.https://10.1080/02635143.2021.1997978

    work page doi:10.1080/02635143.2021.1997978 2023

  21. [22]

    Julie Dangremond Stanton, Kathryn Morris Dye, and Me’Shae Johnson. Knowledge of Learning Makes a Difference: A Comparison of Metacognition in Introductory and Senior-Level Biology Students.CBE—Life Sciences Education, 18(2):ar24, June 2019.https://10.1187/cbe.18-12-0239

    work page doi:10.1187/cbe.18-12-0239 2019

  22. [23]

    Gardner, Tiru S

    Shadi Esnaashari, Lesley A. Gardner, Tiru S. Arthanari, and Michael Rehm. Unfolding self-regulated learning profiles of students: A longitudinal study.Journal of Computer Assisted Learning, 39(4):1116–1131, 2023. https://doi.org/10.1111/jcal.12830. 14 APREPRINT- MAY15, 2026

    work page doi:10.1111/jcal.12830 2023

  23. [24]

    Manita Van Der Stel and Marcel V .J. Veenman. Development of metacognitive skillfulness: A longitudinal study. Learning and Individual Differences, 20(3):220–224, June 2010. https://10.1016/j.lindif.2009.11.005

    work page doi:10.1016/j.lindif.2009.11.005 2010

  24. [25]

    Mohammed Saqr, Sonsoles López-Pernas, Jelena Jovanovi´c, and Dragan Gaševi´c. Intense, turbulent, or wallowing in the mire: A longitudinal study of cross-course online tactics, strategies, and trajectories.The Internet and Higher Education, 57:100902, April 2023.https://10.1016/j.iheduc.2022.100902

    work page doi:10.1016/j.iheduc.2022.100902 2023

  25. [26]

    Manita Van Der Stel and Marcel VJ Veenman. Metacognitive skills and intellectual ability of young adolescents: A longitudinal study from a developmental perspective.European Journal of Psychology of Education, 29(1):117– 137, 2014.https://doi.org/10.1007/s10212-013-0190-5

    work page doi:10.1007/s10212-013-0190-5 2014

  26. [27]

    Analytics of learning strategies: Associations with academic performance and feedback

    Wannisa Matcha, Dragan Gaševi´c, Nora’ayu Ahmad Uzir, Jelena Jovanovi´c, and Abelardo Pardo. Analytics of learning strategies: Associations with academic performance and feedback. InProceedings of the 9th International Conference on Learning Analytics & Knowledge, pages 461–470, 2019. https://doi.org/10.1145/3303772. 3303787

    work page doi:10.1145/3303772 2019

  27. [28]

    Network analytics to unveil links of learning strategies, time management, and academic performance in a flipped classroom.Journal of Learning Analytics, 10(3):64–86, 2023

    Mladen Rakovi´c, Wannisa Matcha, Brendan Eagan, Jelena Jovanovi ´c, David Williamson Shaffer, Abelardo Pardo, Dragan Gaševi´c, et al. Network analytics to unveil links of learning strategies, time management, and academic performance in a flipped classroom.Journal of Learning Analytics, 10(3):64–86, 2023. https: //doi.org/10.18608/jla.2023.7843

    work page doi:10.18608/jla.2023.7843 2023

  28. [29]

    A review of self-regulated learning: Six models and four directions for research.Frontiers in Psychology, 8:422, 2017.https://doi.org/10.3389/fpsyg.2017.00422

    Ernesto Panadero. A review of self-regulated learning: Six models and four directions for research.Frontiers in Psychology, 8:422, 2017.https://doi.org/10.3389/fpsyg.2017.00422

    work page doi:10.3389/fpsyg.2017.00422 2017

  29. [30]

    Susanne de Mooij, Joni Lämsä, Lyn Lim, Olli Aksela, Shruti Athavale, Inti Bistolfi, Flora Jin, Tongguang Li, Roger Azevedo, Maria Bannert, Dragan Gaševi´c, Sanna Järvelä, and Inge Molenaar. A systematic review of self-regulated learning through integration of multimodal data and artificial intelligence.Educational Psychology Review, 37(2):54, 2025.https:/...

    work page doi:10.1007/s10648-025-10028-0 2025

  30. [31]

    Inge Molenaar, Susanne de Mooij, Roger Azevedo, Maria Bannert, Sanna Järvelä, and Dragan Gaševi´c. Measuring self-regulated learning and the role of ai: Five years of research using multimodal multichannel data.Computers in Human Behavior, 139:107540, 2023.https://doi.org/10.1016/j.chb.2022.107540

    work page doi:10.1016/j.chb.2022.107540 2023

  31. [32]

    Process mining techniques for analysing patterns and strategies in students’ self-regulated learning.Metacognition and learning, 9:161–185, 2014

    Maria Bannert, Peter Reimann, and Christoph Sonnenberg. Process mining techniques for analysing patterns and strategies in students’ self-regulated learning.Metacognition and learning, 9:161–185, 2014. https: //doi.org/10.1007/s11409-013-9107-6

    work page doi:10.1007/s11409-013-9107-6 2014

  32. [33]

    Learning strategies, study skills, and self-regulated learning in postsecondary education

    Philip H Winne. Learning strategies, study skills, and self-regulated learning in postsecondary education. In Higher Education: Handbook of Theory and Research: Volume 28, pages 377–403. 2013. https://doi.org/ 10.1007/978-94-007-5836-0_8

    work page doi:10.1007/978-94-007-5836-0_8 2013

  33. [34]

    Using learner trace data to understand metacognitive processes in writing from multiple sources

    Mladen Rakovic, Yizhou Fan, Joep van der Graaf, Shaveen Singh, Jonathan Kilgour, Lyn Lim, Johanna Moore, Maria Bannert, Inge Molenaar, and Dragan Gasevic. Using learner trace data to understand metacognitive processes in writing from multiple sources. InLAK22: 12th International Learning Analytics and Knowledge Conference, page 130–141, 2022.https://doi.o...

    work page doi:10.1145/3506860.3506876 2022

  34. [35]

    Measuring secondary education students’ self-regulated learning processes with digital trace data.Learning and Individual Differences, 118:102625, February 2025

    Joni Lämsä, Susanne De Mooij, Olli Aksela, Shruti Athavale, Inti Bistolfi, Roger Azevedo, Maria Bannert, Dragan Gasevic, Inge Molenaar, and Sanna Järvelä. Measuring secondary education students’ self-regulated learning processes with digital trace data.Learning and Individual Differences, 118:102625, February 2025. https://10.1016/j.lindif.2024.102625

    work page doi:10.1016/j.lindif.2024.102625 2025

  35. [36]

    Zepter, Pia Königs, and Alexandra Budke

    Diana Gebele, Alexandra L. Zepter, Pia Königs, and Alexandra Budke. Metacognition in argumentative writing based on multiple sources in geography education.European Journal of Investigation in Health, Psychology and Education, 12(8):948–974, 2022.https://www.mdpi.com/2254-9625/12/8/69

    work page 2022

  36. [37]

    The effect of self-regulated strategy education on the writing skills of middle school students

    Tuncay Türkben. The effect of self-regulated strategy education on the writing skills of middle school students. International Journal of Education and Literacy Studies, 9(2):52–65, 2021. https://files.eric.ed.gov/ fulltext/EJ1303714.pdf

    work page 2021

  37. [38]

    Analytics of time management and learning strategies for effective online learning in blended environments

    Nora’ayu Ahmad Uzir, Dragan Gaševi´c, Jelena Jovanovi´c, Wannisa Matcha, Lisa-Angelique Lim, and Anthea Fudge. Analytics of time management and learning strategies for effective online learning in blended environments. InProceedings of the 10th International Conference on Learning Analytics & Knowledge, pages 392–401, 2020. https://doi.org/10.1145/3375462.3375493

    work page doi:10.1145/3375462.3375493 2020

  38. [39]

    Combining analytic methods to unlock sequential and temporal patterns of self-regulated learning

    John Saint, Dragan Gaševi´c, Wannisa Matcha, Nora’Ayu Ahmad Uzir, and Abelardo Pardo. Combining analytic methods to unlock sequential and temporal patterns of self-regulated learning. InProceedings of the 10th International Conference on Learning Analytics & Knowledge, pages 402–411, 2020. https://doi.org/10. 1145/3375462.3375487. 15 APREPRINT- MAY15, 2026

    work page arXiv 2020

  39. [40]

    Ed Fincham, Dragan Gaševi´c, Jelena Jovanovi´c, and Abelardo Pardo. From study tactics to learning strategies: An analytical method for extracting interpretable representations.IEEE Transactions on Learning Technologies, 12(1):59–72, 2018.https://doi.org/10.1109/TLT.2018.2823317

    work page doi:10.1109/tlt.2018.2823317 2018

  40. [41]

    Ferreira and Daniel Gillblad

    Diogo R. Ferreira and Daniel Gillblad. Discovering Process Models from Unlabelled Event Logs. In Umesh- war Dayal, Johann Eder, Jana Koehler, and Hajo A. Reijers, editors,Business Process Management, volume 5701, pages 143–158. Springer Berlin Heidelberg, Berlin, Heidelberg, 2009. https://doi.org/10.1007/ 978-3-642-03848-8_11

    work page 2009

  41. [42]

    Armstrong

    Richard A. Armstrong. When to use the bonferroni correction.Ophthalmic and Physiological Optics, 34(5):502– 508, 2014.https://doi.org/10.1111/opo.12131

    work page doi:10.1111/opo.12131 2014

  42. [43]

    Yizhou Fan, Luzhen Tang, Huixiao Le, Kejie Shen, Shufang Tan, Yueying Zhao, Yuan Shen, Xinyu Li, and Dragan Gaševi´c. Beware of metacognitive laziness: Effects of generative artificial intelligence on learning motivation, processes, and performance.British Journal of Educational Technology, 56(2):489–530, 2025. https://doi.org/10.1111/bjet.13544. 16

    work page doi:10.1111/bjet.13544 2025