From Natural Language to Reflective Practice in AI-Supported Conflict Management Training
Parole chiave:
Educational datafication; Interpretability; Small language models; Conflict management; Teacher trainingAbstract
The use of language models in teacher training raises questions about how situated responses become data and how their interpretation can support learning. This paper presents a conceptual and methodological analysis of a proposed extension of ACCORD, a single-player serious game for training teachers to manage intercultural conflicts in school settings. The existing game combines predefined responses based on Rahim’s conflict-management framework with tutoring and debriefing focused on situational appropriateness. A future integration of a small language model (SLM) could allow teachers to formulate their own responses, creating greater expressive freedom while requiring careful interpretation of their language. The paper examines the conditions under which these interpretations could support self-reflection and self-regulation. Ongoing work compares SLM classifications with expert judgements to guide refinement before a possible integration into the game. The analysis distinguishes classification consistency, situational appropriateness and formative value, addressing ambiguity, possible biases and transparency in the use of language data. Teachers’ opportunities to examine and question feedback are central to the proposal, whose contribution to reflective engagement remains to be evaluated.
Riferimenti bibliografici
Artstein, R., & Poesio, M. (2008). Inter-coder agreement for computational linguistics. Computa-tional Linguistics, 34(4), 555–596. https://doi.org/10.1162/coli.07-034-R2
Bandura, A. (2001). Social cognitive theory: An agentic perspective. Annual Review of Psychology, 52, 1–26. https://doi.org/10.1146/annurev.psych.52.1.1
Barbieri, U., Di Fuccio, R., Limone, P., Marocco, D., & Dell’Aquila, E. (2026). From scripted to adaptive serious games: On-device language models for conflict training. In Proceedings of the 18th International Conference on Computer Supported Education, 734–741). SciTePress. https://doi.org/10.5220/0015090900004021
Carless, D., & Boud, D. (2018). The development of student feedback literacy: Enabling uptake of feedback. Assessment & Evaluation in Higher Education, 43(8), 1315–1325. https://doi.org/10.1080/02602938.2018.1463354
Dell’Aquila, E., Vallone, F., Zurlo, M. C., & Marocco, D. (2022). SG-ACCORD: Designing virtual agents for soft skills training in the school context. Education Sciences, 12(3), 174. https://doi.org/10.3390/educsci12030174
Dell’Aquila, E., Marocco, D., Di Fuccio, R., Limone, P., & Barbieri, U. (2026). Natural Teacher Language for Conflict Style Classification with SLMs. In Proceedings of HELMeTO 2026 [In press].
Kane, M. T. (2013). Validating the interpretations and uses of test scores. Journal of Educational Measurement, 50(1), 1–73. https://doi.org/10.1111/jedm.12000
Rahim, M. A. (2002). Toward a theory of managing organizational conflict. International journal of conflict management, 13(3), 206-235. https://doi.org/10.1108/eb022874
Slade, S., & Prinsloo, P. (2013). Learning analytics: Ethical issues and dilemmas. American Behav-ioral Scientist, 57(10), 1510–1529. https://doi.org/10.1177/0002764213479366
Zimmerman, B. J. (2002). Becoming a self-regulated learner: An overview. Theory Into Practice, 41(2), 64–70. https://doi.org/10.1207/s15430421tip4102_2.
##submission.downloads##
Pubblicato
Come citare
Fascicolo
Sezione
Licenza
Copyright (c) 2026 Elena Dell'Aquila, Davide Marocco , Raffaele Di Fuccio, Pierpaolo Limone, Umberto Barbieri

Questo lavoro è fornito con la licenza Creative Commons Attribuzione - Non commerciale - Non opere derivate 4.0 Internazionale.