This study explores the use of Narrative Insight, a personalised GPT model, to analyse undergraduate students' journals in the context of secondary-tertiary transition in mathematics education. The goal is to evaluate the extent to which artificial intelligence can support the researcher in narrative analysis by identifying relevant themes to categorise keywords and highlight emerging themes from student texts. The results show that Narrative Insight can offer new thematic perspectives, although it requires human supervision to ensure accurate interpretations. The model has proven to be a promising tool for automating part of the analytical process for qualitative data, especially in its preliminary stages, without giving up the depth of the research.

ChatGPT is going to replace us! Or not? "Narrative Insight" about secondary-tertiary transition in mathematics

Gaia Turconi;Domenico Brunetto;Giulia Bernardi
2025-01-01

Abstract

This study explores the use of Narrative Insight, a personalised GPT model, to analyse undergraduate students' journals in the context of secondary-tertiary transition in mathematics education. The goal is to evaluate the extent to which artificial intelligence can support the researcher in narrative analysis by identifying relevant themes to categorise keywords and highlight emerging themes from student texts. The results show that Narrative Insight can offer new thematic perspectives, although it requires human supervision to ensure accurate interpretations. The model has proven to be a promising tool for automating part of the analytical process for qualitative data, especially in its preliminary stages, without giving up the depth of the research.
2025
Proceedings of the Fourteenth Congress of European Research in Mathematics Education (CERME14)
qualitative analysis, narrative analysis, AI, secondary-tertiary transition
File in questo prodotto:
File Dimensione Formato  
Turconi_Brunetto_Bernardi_TWG08-Turconi-761_pp1359-1366.pdf

accesso aperto

: Publisher’s version
Dimensione 568.08 kB
Formato Adobe PDF
568.08 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11311/1302491
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact