EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

On Using GeoGebra and ChatGPT for Geometric Discovery

Francisco Botana, Tomas Recio, María Pilar Vélez

Computers · 30.07.2024 · 13 (8) · 187

DOI: 10.3390/computers13080187 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computers, online erschienen am 30.07.2024. Verfasst von Francisco Botana und 2 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Spanish MICINN.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper explores the performance of ChatGPT and GeoGebra Discovery when dealing with automatic geometric reasoning and discovery. The emergence of Large Language Models has attracted considerable attention in mathematics, among other fields where intelligence should be present. We revisit a couple of elementary Euclidean geometry theorems discussed in the birth of Artificial Intelligence and a non-trivial inequality concerning triangles. GeoGebra succeeds in proving all these selected examples, while ChatGPT fails in one case. Our thesis is that both GeoGebra and ChatGPT could be used as complementary systems, where the natural language abilities of ChatGPT and the certified computer algebra methods in GeoGebra Discovery can cooperate in order to obtain sound and—more relevant—interesting results.

Förderung

  • the Spanish MICINN

Zitieren

APA

Botana, F., Recio, T., & Vélez, M. P. (2024). On Using GeoGebra and ChatGPT for Geometric Discovery. Computers, 13(8), 187. https://doi.org/10.3390/computers13080187

Vancouver

Botana F, Recio T, Vélez MP. On Using GeoGebra and ChatGPT for Geometric Discovery. Computers. 2024;13(8):187. doi:10.3390/computers13080187

BibTeX
@article{Botana2024,
  author = {Botana, Francisco and Recio, Tomas and Vélez, María Pilar},
  title = {On Using GeoGebra and ChatGPT for Geometric Discovery},
  journal = {Computers},
  year = {2024},
  volume = {13},
  number = {8},
  pages = {187},
  doi = {10.3390/computers13080187}
}
Kostenlos starten →