CoChat
Sign Up
Cited by 36Teaching and Learning ProgrammingIntelligent Tutoring Systems and Adaptive LearningInnovative Teaching and Learning Methods

How self-regulated learning Is affected by feedback based on large language models: Data-driven sustainable development in computer programming learning

Open access
Sun, Di, Xu, Pengfei, Zhang, Jing, Liu, Ruqi, Zhang, Jun·2025·Electronics
DOI 10.3390/electronics14010194
Open this paper in CoChat — free accountOpen PDF

Abstract

Self-regulated learning (SRL) is a sustainable development skill that involves learners actively monitoring and adjusting their learning processes, which is essential for lifelong learning. Learning feedback plays a crucial role in SRL by aiding in self-observation and self-judgment. In this context, large language models (LLMs), with their ability to use human language and continuously interact with learners, not only provide personalized feedback but also offer a data-driven approach to sustainable development in education. By leveraging real-time data, LLMs have the potential to deliver more effective and interactive feedback that enhances both individual learning experiences and scalable, long-term educational strategies. Therefore, this study utilized a quasi-experimental design to examine the effects of LLM-based feedback on learners’ SRL, aiming to explore how this data-driven application could support learners’ sustainable development in computer programming learning. The findings indicate that LLM-based feedback significantly improves learners’ SRL by providing tailored, interactive support that enhances motivation and metacognitive strategies. Additionally, learners receiving LLM-based feedback demonstrated better academic performance, suggesting that these models can effectively support learners’ sustainable development in computer programming learning. However, the study acknowledges limitations, including the short experimental period and the initial unfamiliarity with LLM tools, which may have influenced the results. Future research should focus on refining LLM integration, exploring the impact of different feedback types, and extending the application of these tools to other educational contexts.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/electronics14010194

Cites

12 of 12 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Passive acceptance of AI-generated responses can erode critical thinking and analytical processes central to PBL.

    “Such passive acceptance of AI-generated responses can erode critical thinking and analytical processes central to PBL (Kadaruddin, 2023;Sun et al., 2025).”

    From Measuring undergraduate students’ reliance on generative AI during problem-solving: Scale development and validation. (2025) · cites this paper as Sun et al., 2025

    The paper’s prompt-design discussion (page unavailable in our copy) warns that one-step prompts providing easy answers may undermine learning, and Section 5.3 suggests possible overreliance on LLM feedback. It does not specifically establish erosion of critical thinking or analytical processes in problem-based learning (PBL). (LLM, conf=0.84)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 37

  1. Zimmerman, B.J. Attaining self-regulation: A social cognitive perspective. In Handbook of Self-Regulation; Boekaerts, M., Pintrich, P.R., Zeidner, M., Eds.; Academic Press: San Diego, CA, USA, 2000; pp. 13-39.
  2. Azevedo, R.; Feyzi-Behnagh, R. Dysregulated Learning with Advanced Learning Technologies. In Proceedings of the 2010 AAAI Fall Symposium Series, Westin Arlington Gateway, Arlington, VA, USA, 11-13 November 2010.
  3. Munshi, A.; Biswas, G.; Baker, R.; Ocumpaugh, J.; Hutt, S.; Paquette, L. Analysing adaptive scaffolds that help students develop self-regulated learning behaviours. J. Comput. Assist. Learn. 2023, 39, 351-368. [CrossRef] · DOI · Paper page
  4. Butler, D.L.; Winne, P.H. Feedback and self-regulated learning: A theoretical synthesis. Rev. Educ. Res. 1995, 65, 245-281. [CrossRef] · DOI · Paper page
  5. Cavalcanti, A.P.; Barbosa, A.; Carvalho, R.; Freitas, F.; Tsai, Y.-S.; Gašević, D.; Mello, R.F. Automatic feedback in online learning environments: A systematic literature review. Comput. Educ. Artif. Intell. 2021, 2, 100027. [CrossRef] · DOI · Paper page
  6. Black, P.; McCormick, R.; James, M.; Pedder, D. Learning How to Learn and Assessment for Learning: A theoretical inquiry. Res. Pap. Educ. 2006, 21, 119-132. [CrossRef] · DOI
  7. Kidane, H.H.; Roebertsen, H.; van der Vleuten, C.P.M. Students' perceptions towards self-directed learning in Ethiopian medical schools with new innovative curriculum: A mixed-method study. BMC Med. Educ. 2020, 20, 7. [CrossRef] · DOI
  8. Azevedo, R. Defining and Measuring Engagement and Learning in Science: Conceptual, Theoretical, Methodological, and Analytical Issues. Educ. Psychol. 2015, 50, 84-94. [CrossRef] · DOI · Paper page
  9. Greene, J.; Azevedo, R. Adolescents' Use of Self-Regulatory Processes and Their Relation to Qualitative Mental Model Shifts While Using Hypermedia. J. Educ. Comput. Res. 2007, 36, 125-148. [CrossRef] · DOI
  10. Winne, P.H.; Hadwin, A.F. Studying as self-regulated learning. In Metacognition in Educational Theory and Practice; The Educational Psychology Series; Lawrence Erlbaum Associates Publishers: Mahwah, NJ, USA, 1998; pp. 277-304.
  11. Khiat, H. Academic performance and the practice of self-directed learning: The adult student perspective. J. Furth. High. Educ. 2015, 41, 44-59. [CrossRef] · DOI
  12. Dent, A.L.; Koenka, A.C. The Relation Between Self-Regulated Learning and Academic Achievement Across Childhood and Adolescence: A Meta-Analysis. Educ. Psychol. Rev. 2016, 28, 425-474. [CrossRef] · DOI
  13. Schunk, D.H.; Greene, J.A. Handbook of Self-Regulation of Learning and Performance, 2nd ed.; Routledge: New York, NY, USA, 2017.
  14. Pintrich, P.R.; Smith, D.A.F.; Garcia, T.; Mckeachie, W.J. Reliability and predictive validity of the motivated strategies for learning questionnaire (Mslq). Educ. Psychol. Meas. 1993, 53, 801-813. [CrossRef] · DOI · Paper page
  15. Cleary, T.J.; Zimmerman, B.J. Self-regulation differences during athletic practice by experts, non-experts, and novices. J. Appl. Sport Psychol. 2001, 13, 185-206. [CrossRef] · DOI · Paper page
  16. Bannert, M.; Hildebrand, M.; Mengelkamp, C. Effects of a metacognitive support device in learning environments. Comput. Hum. Behav. 2009, 25, 829-835. [CrossRef] · DOI
  17. Deekens, V.M.; Greene, J.A.; Lobczowski, N.G. Monitoring and depth of strategy use in computer-based learning environments for science and history. Br. J. Educ. Psychol. 2018, 88, 63-79. [CrossRef] [PubMed] · DOI
  18. Bandura, A. Social cognitive theory of self-regulation. Organ. Behav. Hum. Decis. Process. 1991, 50, 248-287. [CrossRef] · DOI · Paper page
  19. Kesuma, A.T.; Harun, H.; Zamroni, Z.; Putranta, H.; Kistoro, H.C.A. Evaluation of the Self-regulated Learning Model in High Schools: A Systematic Literature Review. Univers. J. Educ. Res. 2020, 8, 4792-4806. [CrossRef] · DOI
  20. Clariana, R.B.; Wagner, D.; Roher Murphy, L.C. Applying a connectionist description of feedback timing. Educ. Technol. Res. Dev. 2000, 48, 5-22. [CrossRef] · DOI
  21. Belcadhi, L.C. Personalized feedback for self assessment in lifelong learning environments based on semantic web. Comput. Hum. Behav. 2016, 55, 562-570. [CrossRef] · DOI
  22. Marin, V.J.; Pereira, T.; Sridharan, S.; Rivero, C.R. Automated Personalized Feedback in Introductory Java Programming MOOCs. In Proceedings of the 2017 IEEE 33rd International Conference on Data Engineering (ICDE), San Diego, CA, USA, 19-22 April 2017; pp. 1259-1270.
  23. Chen, X.; Zou, D.; Cheng, G.; Xie, H. Detecting latent topics and trends in educational technologies over four decades using structural topic modeling: A retrospective of all volumes of Computers & Education. Comput. Educ. 2020, 151, 103855. [CrossRef] · DOI
  24. Peters, M.A. Roboethics in education and society. Educ. Philos. Theory 2019, 52, 11-16. [CrossRef] · DOI
  25. van der Vorst, T.; Jelicic, N. Artificial Intelligence in Education: Can AI bring the full potential of personalized learning to education? In Proceedings of the 30th European Regional ITS Conference, Helsinki, Finland, 6-19 June 2019.
  26. Gupta, R.; Park, J.B.; Herzog, I.; Yosufi, N.; Mangan, A.; Firouzbakht, P.K.; Mailey, B.A. Applying GPT-4 to the Plastic Surgery Inservice Training Examination. J. Plast. Reconstr. Aesthetic Surg. 2023, 87, 78-82. [CrossRef] [PubMed] · DOI
  27. Liu, J.; Zheng, J.; Cai, X.; Wu, D.; Yin, C. A descriptive study based on the comparison of ChatGPT and evidence-based neurosurgeons. iScience 2023, 26, 107590. [CrossRef] [PubMed] · DOI
  28. Takagi, S.; Watari, T.; Erabi, A.; Sakaguchi, K. Performance of GPT-3.5 and GPT-4 on the Japanese Medical Licensing Examination: Comparison Study. JMIR Med Educ. 2023, 9, e48002. [CrossRef] [PubMed] · DOI · Paper page
  29. Kılıç, M.E. AI in Medical Education: A Comparative Analysis of GPT-4 and GPT-3.5 on Turkish Medical Specialization Exam Performance. medRxiv 2023, 2023-07. [CrossRef] · DOI
  30. Guerra, G.A.; Hofmann, H.; Sobhani, S.; Hofmann, G.; Gomez, D.; Soroudi, D.; Hopkins, B.S.; Dallas, J.; Pangal, D.J.; Cheok, S.; et al. GPT-4 Artificial Intelligence Model Outperforms ChatGPT, Medical Students, and Neurosurgery Residents on Neurosurgery Written Board-Like Questions. World Neurosurg. 2023, 179, e160-e165. [CrossRef] · DOI · Paper page
  31. Tsai, M.-L.; Ong, C.W.; Chen, C.-L. Exploring the use of large language models (LLMs) in chemical engineering education: Building core course problem models with Chat-GPT. Educ. Chem. Eng. 2023, 44, 71-95. [CrossRef] · DOI
  32. Li, J.; Meland, P.H.; Notland, J.S.; Storhaug, A.; Tysse, J.H. Evaluating the Impact of ChatGPT on Exercises of a Software Security Course. arXiv 2023, arXiv:2309.10085. · arXiv
  33. Naismith, B.; Mulcaire, P.; Burstein, J. Automated evaluation of written discourse coherence using GPT-4. In Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023), Toronto, ON, Canada, 13 July 2023; pp. 394-403.
  34. Bezirhan, U.; von Davier, M. Automated reading passage generation with OpenAI's large language model. Comput. Educ. Artif. Intell. 2023, 5, 100161. [CrossRef] · DOI
  35. Chen, Y.; Ding, N.; Zheng, H.-T.; Liu, Z.; Sun, M.; Zhou, B. Empowering Private Tutoring by Chaining Large Language Models. arXiv 2023, arXiv:2309.08112. · arXiv
  36. Dan, Y.; Lei, Z.; Gu, Y.; Li, Y.; Yin, J.; Lin, J.; Ye, L.; Tie, Z.; Zhou, Y.; Wang, Y.; et al. EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education. arXiv 2023, arXiv:2308.02773. · arXiv
  37. Dang, H.; Mecke, L.; Lehmann, F.; Goller, S.; Buschek, D. How to prompt? Opportunities and challenges of zero-and few-shot learning for human-AI interaction in creative applications of generative models. arXiv 2022, arXiv:2209.01390. · arXiv

Cited by

Sorted by citations

Authors
Sun, D., Xu, P., Zhang, J., Liu, R., & Zhang, J.
Affiliations
  • Dalian University of Technology (CN)
  • Beijing Normal University (CN)
  • Ministry of Ecology and Environment (CN)
Corresponding author
Zhang, Jun
ORCID
Venue
Electronics
Publisher
MDPI AG
Published
2025-01-05
Volume
14
Issue
1
Pages
194
ISSN
2079-9292 (ISSN-L)
DOI
10.3390/electronics14010194
OpenAlex
W4406102215
Cited by
36
References
12
Citations by year
2026: 23 · 2025: 13
FWCI
21.54
Type
journal article
Language
en
Open access
Licence
Locations
Electronics (publishedVersion, cc-by)
Funders
  • China’s Ministry of Education of Humanities and Social Science project (23YJA880044, 24YJCZH176, 24YJCZH417, 1331004, DUT24LAB130, 71904022, 72074039, 62072067, 62466059)
  • Innovation Funding Project of Engineering Research Center of Integration and Application of Digital Learning Technology of China’s Ministry of Education (23YJA880044, 24YJCZH176, 24YJCZH417, 1331004, DUT24LAB130, 71904022, 72074039, 62072067, 62466059)
  • Fundamental Research Funds for the Central Universities (23YJA880044, 24YJCZH176, 24YJCZH417, 1331004, DUT24LAB130, 71904022, 72074039, 62072067, 62466059)
  • National Natural Science Foundation of China (23YJA880044, 24YJCZH176, 24YJCZH417, 1331004, DUT24LAB130, 71904022, 72074039, 62072067, 62466059)
Topics
  • Physical Sciences › Computer Science › Computer Science Applications › Teaching and Learning Programming
  • Physical Sciences › Computer Science › Artificial Intelligence › Intelligent Tutoring Systems and Adaptive Learning
  • Social Sciences › Psychology › Developmental and Educational Psychology › Innovative Teaching and Learning Methods
Keywords
student self-regulation, large language models, feedback in learning, programming education, personalized feedback, metacognitive strategies, student motivation, academic performance, data-driven education

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review