CoChat
Sign Up
Cited by 65Science Education and PedagogyArtificial Intelligence in EducationIntelligent Tutoring Systems and Adaptive Learning

Generative AI as a Dialogic Partner: Enhancing Multiple Perspectives, Reasoning, and Argumentation in Science Education with Customized Chatbots

Open access
Tang, Kok-Sing, Putra, Gde Buana Sandila·2026·Journal of Science Education and Technology
DOI 10.1007/s10956-025-10240-1
Open this paper in CoChat — free accountOpen PDF

Abstract

This study investigates the potential of customized generative AI (GenAI) chatbots to foster dialogic learning and argumentation in science education. Framed by Bakhtin’s theory of heteroglossia emphasizing the interplay of multiple voices in discourse, a customized chatbot called Dialogic Science Teacher (DST) was deliberately designed to embody dialogic learning principles. This instructional approach positions GenAI as a dialogic partner rather than an authoritative knowledge provider. Using a case study approach, 21 students from two high schools interacted with DST to explore socioscientific issues as they learned physics, chemistry, and biology. Analysis of students’ chatlogs revealed four prominent dialogic characteristics: perspective-taking, reasoning, arguing, and creative thinking. Qualitative findings illustrated how dialogic interactions with DST were characterized by students in critically reflecting, reasoning, arguing, and developing innovative ideas and alternative perspectives in response to challenging scientific problems. Quantitative findings further demonstrated high percentages of these dialogic characteristics in both schools, thus indicating DST’s reach in facilitating dialogic interaction among the students. These findings underscore the significance of embedding dialogic learning principles into GenAI tools, highlighting their potential to encourage critical thinking, argumentation, and co-construction of knowledge in science classroom discourse. The study offers both theoretical and practical insights to ongoing discussions on GenAI’s role as a collaborative learning partner in science education.

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 · 10.1007/s10956-025-10240-1

Cites

4 of 4 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?

  • GenAI-supported feedback may help students improve written products and, when designed dialogically, support deeper reasoning, yet it may also reduce the need for students to make their own evaluative judgments if the feedback process encourages passive uptake.

    “GenAI-supported feedback is pedagogically promising but also potentially risky: it may help students improve written products and, when designed dialogically, support deeper reasoning, yet it may also reduce the need for students to make their own evaluative judgments if the feedback process encourages passive uptake”

    From Human-centered GenAI feedback design in higher education: a multisite experiment on direct, reflective, and hybrid approaches to scientific argumentation (2026) · cites this paper as Tang & Putra, 2025

    Split into 2 atoms — 0 confirmed, 2 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.

    Experimental — accuracy not yet measured

  • Much of the literature on AI-supported feedback has focused on general writing tasks or broad comparisons among feedback sources, whereas disciplinary reasoning in university science courses has received less sustained attention.

    “much of the literature on AI-supported feedback has focused on general writing tasks or broad comparisons among feedback sources, whereas disciplinary reasoning in university science courses has received less sustained attention”

    From Human-centered GenAI feedback design in higher education: a multisite experiment on direct, reflective, and hybrid approaches to scientific argumentation (2026) · cites this paper as Tang & Putra, 2025

    The Introduction discusses comparisons between customized and general-purpose chatbots, while the Research Site and Implementation section describes a study in Indonesian high schools. Neither addresses whether AI-feedback literature concentrates on general writing or comparisons among feedback sources, or whether disciplinary reasoning in university science courses has received less attention. Searches for feedback, writing, and university settings found no passage establishing that literature-wide claim. (LLM, conf=0.72)

    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: 23

  1. Arun, G., Perumal, V., Urias, F. P. J. B., Ler, Y. E., Tan, B. W. T., Vallabhajosyula, R., Tan, E., Ng, O., Ng, K. B., & Mogali, S. R. (2024). ChatGPT versus a customized AI chatbot (Anatbuddy) for anatomy education: A comparative pilot study. Anatomical Sciences Education, 17(7), 1396-1405. https:// doi. org/ 10. 1002/ ase. 2502 · DOI
  2. Bakhtin, M. M. (1981). The dialogic imagination: Four essays. Uni- versity of Texas Press.
  3. Callis-Duehl, K., Idsardi, R., Humphrey, E. A., & Gougis, R. D. (2018). Missed opportunities for science learning: Unacknowledged unscientific arguments in asynchronous online and face-to-face discussions. Journal of Science Education and Technology, 27(1), 86-98. https:// doi. org/ 10. 1007/ s10956-017-9710-4 · DOI
  4. Cavlazoglu, B., & Stuessy, C. (2018). Examining science teachers' argumentation in a teacher workshop on earthquake engineering. Journal of Science Education and Technology, 27(4), 348-361. https:// doi. org/ 10. 1007/ s10956-018-9728-2 · DOI
  5. Chang, J., Park, J., & Park, J. (2023b). Using an artificial intelligence chatbot in scientific inquiry: Focusing on a guided-inquiry activity using inquirybot. Asia-Pacific Science Education, 9(1), 44-74. https:// doi. org/ 10. 1163/ 23641 177-bja10 062 · DOI
  6. Chin, C. (2007). Teacher questioning in science classrooms: Approaches that stimulate productive thinking. Journal of Research in Science Teaching, 44(6), 815-843. https:// doi. org/ 10. 1002/ tea. 20171 · DOI · Paper page
  7. Dickerson, P. (2024). Learning with Socrates: How generative AI and ancient pedagogy can develop students' critical thinking skills. In H. Crompton & D. Burke (Eds.), Artificial intelligence applica- tions in higher education: Theories, ethics, and case studies for universities. Routledge. https:// doi. org/ 10. 4324/ 97810 03440 178-6 · DOI
  8. González-Howard, M., & McNeill, K. L. (2020). Acting with epistemic agency: Characterizing student critique during argumentation dis- cussions. Science Education, 104(6), 953-982. https:// doi. org/ 10. 1002/ sce. 21592 · DOI
  9. Kelly, G. J. (2007). Discourse in science classrooms. In S. K. Abell & N. G. Lederman (Eds.), Handbook of research on science educa- tion (pp. 443-469). Lawrence Erlbaum Associates. http:// www. loc. gov/ catdir/ enhan cemen ts/ fy0701/ 20060 31809-t. html
  10. Kelly, G. J., & Licona, P. (2018). Epistemic practices and science edu- cation. In M. R. Matthews (Ed.), History, philosophy and sci- ence teaching (pp. 139-165). Springer. https:// doi. org/ 10. 1007/ 978-3-319-62616-1_5 · DOI
  11. Kwon, M. (2024). Development of a customized GPTs-based chatbot for pre-service teacher education and analysis of its educational performance in mathematics. Mathematical Education, 63(3), 467-484. https:// doi. org/ 10. 7468/ mathe du. 2024. 63.3. 467 · DOI
  12. Mayweg-Paus, E., Thiebach, M., & Jucks, R. (2016). Let me criti- cally question this! -Insights from a training study on the role of questioning on argumentative discourse. International Journal of Educational Research, 79, 195-210. https:// doi. org/ 10. 1016/j. ijer. 2016. 05. 017 · DOI
  13. Mortimer, E. F., & Scott, P. (2003). Meaning making in secondary science classrooms. Open University Press.
  14. National Research Council. (2012). A framework for K-12 science education: Practices, crosscutting concepts, and core ideas. The National Academies Press. http:// www. nap. edu/ openb ook. php? record_ id= 13165
  15. Ng, D. T. K., Tan, C. W., & Leung, J. K. L. (2024). Empowering student self-regulated learning and science education through ChatGPT: A pioneering pilot study. British Journal of Educa- tional Technology, 55(4), 1328-1353. https:// doi. org/ 10. 1111/ bjet. 13454 · DOI
  16. Stake, R. E. (2000). Case studies. In N. Denzin & Y. Lincoln (Eds.), Handbook of qualitative research (2nd ed., pp. 435-454). Sage.
  17. Tang, K. S. (2020). The Use of Epistemic Tools to Facilitate Epistemic Cognition & Metacognition in Developing Scientific Explanation. Cognition & Instruction, 38(4), 474-502. https:// doi. org/ 10. 1080/ 07370 008. 2020. 17458 · DOI
  18. Tang, K.S. (2024). Informing research on generative artificial intelli- gence from a language and literacy perspective: A meta-synthesis of studies in science education. Science Education, 108(5), 1329- 1355. https:// doi. org/ 10. 1002/ sce. 21875 · DOI
  19. Tang, K.S. (2025). AI-textuality: Expanding Intertextuality to Theorize Human-AI Interaction with Generative AI, Applied Linguistics. https:// doi. org/ 10. 1093/ applin/ amaf0 16 · DOI
  20. Tang, K.S. & Cooper, G. (2024). The role of materiality in an era of generative artificial intelligence. Science & Education. https:// doi. org/ 10. 1007/ s11191-024-00508-0 · DOI
  21. Tang, K.S. Cooper, G., Rappa, N., Cooper, M., Sims, C., & Nonis, K. (2024). A Dialogic Approach to Transform Teaching, Learning & Assessment with Generative AI in Secondary Education: A Proof of Concept. Pedagogies: An International Journal, 19(3), 492-503.https:// doi. org/ 10. 1080/ 15544 80X. 2024. 23797 · DOI · Paper page
  22. Tytler, R., & Aranda, G. (2015). Expert teachers' discursive moves in science classroom interactive talk [journal article]. International Journal of Science and Mathematics Education, 13(2), 425-446. https:// doi. org/ 10. 1007/ s10763-015-9617-6 · DOI
  23. Zhai, X., & Krajcik, J. (2024). Uses of artificial intelligence in STEM education. Oxford University Press.

Cited by

Sorted by citations

Authors
Tang, K.-S., & Putra, G. B. S.
Affiliations
Curtin University (AU)
Corresponding author
Tang, Kok-Sing
ORCID
Venue
Journal of Science Education and Technology
Publisher
Springer Science and Business Media LLC
Published
2025-07-18
Volume
35
Issue
1
Pages
128-140
ISSN
  • 1059-0145 (ISSN-L)
  • 1573-1839
DOI
10.1007/s10956-025-10240-1
OpenAlex
W4413060535
Cited by
65
References
4
Citations by year
2026: 58 · 2025: 7
FWCI
201.11
Type
journal article
Language
en
Open access
Licence
Locations
Journal of Science Education and Technology (publishedVersion, cc-by)
Funders
Curtin University
Topics
  • Social Sciences › Education › Science Education and Pedagogy
  • Physical Sciences › Computer Science › Information Systems › Artificial Intelligence in Education
  • Physical Sciences › Computer Science › Artificial Intelligence › Intelligent Tutoring Systems and Adaptive Learning
Keywords
generative AI chatbots, dialogic learning, argumentation, heteroglossia, Bakhtin, socioscientific issues, perspective taking, critical thinking, creative thinking, science classroom discourse, co-construction of knowledge, high school science 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