Toward cyclic A.I. modelling of self-regulated learning: a case study with e-learning trace data

Andrew Schwabe; Özgür Akgün; Ella Haig

Toward cyclic A.I. modelling of self-regulated learning: a case study with e-learning trace data

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Many e-learning platforms assert their ability or potential to improve students' self-regulated learning (SRL), however the cyclical and undirected nature of SRL theoretical models represent significant challenges for representation within contemporary machine learning frameworks. We apply SRL-informed features to trace data in order to advance modelling of students' SRL activities, to improve predictability and explainability regarding the causal effects of learning in an eLearning environment. We demonstrate that these features improve predictive accuracy and validate the value of further research into cyclic modelling techniques for SRL.

Original language	English
Title of host publication	Thirty-second international conference on learning
Subtitle of host publication	University of Granada, School of Education, Granada, Spain, 18 - 20, June 2025
Editors	José Luis Ortega-Martín, Bill Cope, Mary Kalntzis
Number of pages	6
ISBN (Electronic)	9781969318351
Publication status	Published - 16 Mar 2026
Event	Thirty-Second International Conference on Learning - Granada, Spain Duration: 8 Jul 2025 → 10 Jul 2025 Conference number: 32 https://thelearner.com/about/history/2025-conference#block-3

Publication series

Name	The learner conference proceedings series

Conference

Conference	Thirty-Second International Conference on Learning
Country/Territory	Spain
City	Granada
Period	8/07/25 → 10/07/25
Internet address	https://thelearner.com/about/history/2025-conference#block-3

Keywords

Artificial intelligence
Machine learning
Self regulated learning

Access to Document

https://arxiv.org/abs/2507.02913Licence: Other

Handle.net

Persistent link to portal record

Cite this

Schwabe, A., Akgün, Ö., & Haig, E. (2026). Toward cyclic A.I. modelling of self-regulated learning: a case study with e-learning trace data. In J. L. Ortega-Martín, B. Cope, & M. Kalntzis (Eds.), Thirty-second international conference on learning: University of Granada, School of Education, Granada, Spain, 18 - 20, June 2025 (The learner conference proceedings series). https://arxiv.org/abs/2507.02913

Schwabe, Andrew ; Akgün, Özgür ; Haig, Ella. / Toward cyclic A.I. modelling of self-regulated learning : a case study with e-learning trace data. Thirty-second international conference on learning: University of Granada, School of Education, Granada, Spain, 18 - 20, June 2025. editor / José Luis Ortega-Martín ; Bill Cope ; Mary Kalntzis. 2026. (The learner conference proceedings series).

@inproceedings{21fe9ea250b44d75a6a5c0fc361859d3,

title = "Toward cyclic A.I. modelling of self-regulated learning: a case study with e-learning trace data",

abstract = "Many e-learning platforms assert their ability or potential to improve students' self-regulated learning (SRL), however the cyclical and undirected nature of SRL theoretical models represent significant challenges for representation within contemporary machine learning frameworks. We apply SRL-informed features to trace data in order to advance modelling of students' SRL activities, to improve predictability and explainability regarding the causal effects of learning in an eLearning environment. We demonstrate that these features improve predictive accuracy and validate the value of further research into cyclic modelling techniques for SRL. ",

keywords = "Artificial intelligence, Machine learning, Self regulated learning",

author = "Andrew Schwabe and {\"O}zg{\"u}r Akg{\"u}n and Ella Haig",

year = "2026",

month = mar,

day = "16",

language = "English",

isbn = "9781969318344",

series = "The learner conference proceedings series",

editor = "Ortega-Mart{\'i}n, \{Jos{\'e} Luis\} and Bill Cope and Mary Kalntzis",

booktitle = "Thirty-second international conference on learning",

note = "Thirty-Second International Conference on Learning ; Conference date: 08-07-2025 Through 10-07-2025",

url = "https://thelearner.com/about/history/2025-conference\#block-3",

}

Schwabe, A , Akgün, Ö & Haig, E 2026, Toward cyclic A.I. modelling of self-regulated learning: a case study with e-learning trace data. in JL Ortega-Martín, B Cope & M Kalntzis (eds), Thirty-second international conference on learning: University of Granada, School of Education, Granada, Spain, 18 - 20, June 2025. The learner conference proceedings series, Thirty-Second International Conference on Learning, Granada, Spain, 8/07/25. <https://arxiv.org/abs/2507.02913>

Toward cyclic A.I. modelling of self-regulated learning: a case study with e-learning trace data. / Schwabe, Andrew ; Akgün, Özgür; Haig, Ella.
Thirty-second international conference on learning: University of Granada, School of Education, Granada, Spain, 18 - 20, June 2025. ed. / José Luis Ortega-Martín; Bill Cope; Mary Kalntzis. 2026. (The learner conference proceedings series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Toward cyclic A.I. modelling of self-regulated learning

T2 - Thirty-Second International Conference on Learning

AU - Schwabe, Andrew

AU - Akgün, Özgür

AU - Haig, Ella

N1 - Conference code: 32

PY - 2026/3/16

Y1 - 2026/3/16

N2 - Many e-learning platforms assert their ability or potential to improve students' self-regulated learning (SRL), however the cyclical and undirected nature of SRL theoretical models represent significant challenges for representation within contemporary machine learning frameworks. We apply SRL-informed features to trace data in order to advance modelling of students' SRL activities, to improve predictability and explainability regarding the causal effects of learning in an eLearning environment. We demonstrate that these features improve predictive accuracy and validate the value of further research into cyclic modelling techniques for SRL.

AB - Many e-learning platforms assert their ability or potential to improve students' self-regulated learning (SRL), however the cyclical and undirected nature of SRL theoretical models represent significant challenges for representation within contemporary machine learning frameworks. We apply SRL-informed features to trace data in order to advance modelling of students' SRL activities, to improve predictability and explainability regarding the causal effects of learning in an eLearning environment. We demonstrate that these features improve predictive accuracy and validate the value of further research into cyclic modelling techniques for SRL.

KW - Artificial intelligence

KW - Machine learning

KW - Self regulated learning

UR - https://doi.org/10.18848/LRNRP/CP4

UR - https://cgscholar.com/publishers/conference-proceedings/thirty-second-international-conference-on-learning

M3 - Conference contribution

SN - 9781969318344

T3 - The learner conference proceedings series

BT - Thirty-second international conference on learning

A2 - Ortega-Martín, José Luis

A2 - Cope, Bill

A2 - Kalntzis, Mary

Y2 - 8 July 2025 through 10 July 2025

ER -

Toward cyclic A.I. modelling of self-regulated learning: a case study with e-learning trace data

Abstract

Publication series

Conference

Keywords

Access to Document

Handle.net

Other files and links

Fingerprint

Cite this