CoChat

Generative AI and multimodal data for educational feedback: Insights from embodied math learning

Open access
Cosentino, Giulia, Anton, Jacqueline, Sharma, Kshitij, Gelsomini, Mirko, Giannakos, Michail, Abrahamson, Dor · 2025 · British Journal of Educational Technology
Cited by 54

The DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.

Abstract

This study explores the role of generative AI (GenAI) in providing formative feedback in children's digital learning experiences, specifically in the context of mathematics education. Using multimodal data, the research compares AI‐generated feedback with feedback from human instructors, focusing on its impact on children's learning outcomes. Children engaged with a digital body‐scale number line to learn addition and subtraction of positive and negative integers through embodied interaction. The study followed a between‐group design, with one group receiving feedback from a human instructor and the other from GenAI. Eye‐tracking data and system logs were used to evaluate student's information processing behaviour and cognitive load. The results revealed that while task‐based performance did not differ significantly between conditions, the GenAI feedback condition demonstrated lower cognitive load and students show different visual information processing strategies among the two conditions. The findings provide empirical support for the potential of GenAI to complement traditional teaching by providing structured and adaptive feedback that supports efficient learning. The study underscores the importance of hybrid intelligence approaches that integrate human and AI feedback to enhance learning through synergistic feedback. This research offers valuable insights for educators, developers and researchers aiming to design hybrid AI‐human educational environments that promote effective learning outcomes. Practitioner notes: What is already known about this topic? Embodied learning approaches have been shown to facilitate deeper cognitive processing by engaging students physically with learning materials, which is especially beneficial in abstract subjects like mathematics. GenAI has the potential to enhance educational experiences through personalized feedback, making it crucial for fostering student understanding and engagement. Previous research indicates that hybrid intelligence that combines AI with human instructors can contribute to improved educational outcomes. What this paper adds? This study empirically examines the effectiveness of GenAI‐generated feedback when compared to human instructor feedback in the context of a multisensory environment (MSE) for math learning. Findings from system logs and eye‐tracking analysis reveal that GenAI feedback can support learning effectively, particularly in helping students manage their cognitive load. The research uncovers that GenAI and teacher feedback lead to different information processing strategies. These findings provide actionable insights into how feedback modality influences cognitive engagement. Implications for practice and/or policy The integration of GenAI into educational settings presents an opportunity to enhance traditional teaching methods, enabling an adaptive learning environment that leverages the strengths of both AI and human feedback. Future educational practices should explore hybrid models that incorporate both AI and human feedback to create inclusive and effective learning experiences, adapting to the diverse needs of learners. Policymakers should establish guidelines and frameworks to facilitate the ethical and equitable adoption of GenAI technologies for learning. This includes addressing issues of trust, transparency and accessibility to ensure that GenAI systems are effectively supporting, rather than replacing, human instructors.

Overview

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

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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

Integrity signals

Registry

Crossref · 10.1111/bjet.13587

Cites

12 of 12 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

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

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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

Self-check

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

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

Citations

Cites

Research works printed but not linked: 48

  1. 10.1186/s41235-016-0034-3 · DOI · Paper page
  2. 10.1159/000443153 · DOI
  3. 10.1145/3027385.3027429 · DOI
  4. 10.1016/j.ijhcs.2023.103030 · DOI
  5. Bofferding L., 2014, International Group for the Psychology of Mathematics Education
  6. 10.1145/3501712.3535294 · DOI
  7. 10.1111/bjet.13525 · DOI
  8. 10.1145/3585088.3589385 · DOI
  9. 10.1109/TLT.2023.3243210 · DOI
  10. Csikszentmihalyi M., 2020, Finding flow: The psychology of engagement with everyday life
  11. Czikszentmihalyi M., 1990, Flow: The psychology of optimal experience
  12. 10.1007/s10639-022-11486-7 · DOI · Paper page
  13. Gelsomini M., 2023, Sensei—Experience in all senses. Multisensory and multimodal research framework
  14. 10.1111/bjet.13320 · DOI
  15. Giannakos M. N., 2020, Movement forward: The continued growth of child‐computer interaction research
  16. Ginsburg H., 1997, Not a cookbook: Guidelines for conducting a clinical interview, 115
  17. 10.1007/978‐3‐030‐52237‐7 · DOI
  18. Huang Y., 2019, Human‐AI co‐learning for datadriven AI, CoRR
  19. 10.1007/978-981-16-2327-1_115-1 · DOI
  20. 10.37398/JSR.2020.640137 · DOI
  21. 10.1007/s11423-024-10342-4 · DOI
  22. 10.4324/9781315798844 · DOI · Paper page
  23. 10.1016/j.ijcci.2021.100355 · DOI
  24. 10.1111/bjet.12861 · DOI · Paper page
  25. 10.1007/s10055-023-00903-y · DOI
  26. Moyer‐PackenhaM P. S., 2015, Young children's learning performance and efficiency when using virtual manipulative mathematics ipad apps, Journal of Computers in Mathematics and Science Teaching, 34, 41
  27. 10.1007/s11042-022-12296-2 · DOI
  28. 10.1207/S15326985EP3801_1 · DOI · Paper page
  29. 10.1037//0022‐0663.86.1.122 · doi:10.1037//0022-0663.86.1.122 · Paper page
  30. 10.1145/1743666.1743701 · DOI · Paper page
  31. 10.7312/piag91272 · DOI · Paper page
  32. 10.1177/1555412013496894 · DOI · Paper page
  33. Shapiro L., 2019, The oxford handbook of cognitive science, 118
  34. 10.3389/frai.2021.713176 · DOI
  35. 10.1075/aicr.82 · doi:10.1075/aicr.82
  36. 10.1111/jcal.12473 · DOI · Paper page
  37. 10.1007/s10758-014-9212-x · DOI
  38. Suraworachet W. Seon J. &Cukurova M.(2024).Predicting challenge moments from students’ discourse: A comparison of GPT‐4 to two traditional natural language processing approaches. Proceedings of the 14th Learning Analytics and Knowledge Conference 473–485.https://doi.org/10.1145/3636555.3636905 · DOI
  39. 10.1007/978-1-4614-6977-3_4 · DOI
  40. 10.3389/frbhe.2024.1384713 · DOI
  41. 10.1007/978-1-4419-5546-3_10 · DOI
  42. 10.1016/j.cognition.2011.08.005 · DOI
  43. 10.1186/s40561‐018‐0071‐0 · DOI · Paper page
  44. 10.1016/j.ijcci.2021.100406 · DOI
  45. 10.1007/s11042‐024‐19814‐4 · DOI
  46. Yang C., 2018, Comparison of animation and static‐picture based instruction: Effects on performance and cognitive load for learning genetics, Journal of Educational Technology & Society, 21, 1
  47. 10.1016/j.caeai.2022.100061 · DOI · Paper page
  48. 10.1111/jcal.12892 · DOI · Paper page

Cited by

See all 54

Metadata

Authors
Cosentino, G., Anton, J., Sharma, K., Gelsomini, M., Giannakos, M., & Abrahamson, D.
Venue
British Journal of Educational Technology
Publisher
Wiley
Published
2025-04-21
Volume
56
Issue
5
Pages
1686-1709
ISSN
  • 0007-1013 (ISSN-L)
  • 1467-8535
OpenAlex
W4409629882
Cited by
54
References
12
FWCI
22.47
Type
journal article
Language
en
Open access
bronze

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

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.