Authors:
Lidiane Silva
1
;
Eduardo Alves Lima Caldas
2
;
Marcos Vinícius de Freitas Borges
3
;
Adson Roberto Pontes Damasceno
4
and
Francisco Oliveira
1
Affiliations:
1
UECE - State University of Ceara, Fortaleza, Brazil
;
2
UFC - Federal University of Ceará, Fortaleza, Brazil
;
3
IFMA - Federal Institute of Maranhão, São Luís, Brazil
;
4
UECE - State University of Ceara, Mombaça, Brazil
Keyword(s):
Distance Learning, Generative Artificial Intelligence, Learning Styles, Content Production.
Abstract:
The use of generative AI can be a powerful ally in combating dropout rates in online courses. This study explores the application of artificial intelligence (AI) to personalize educational content, aligning texts with the learning styles identified by David Kolb (Converging, Diverging, Assimilating, and Accommodating). This research proposes a generative AI algorithm capable of creating texts tailored to these styles, specifically designed for distance education (DE), in which personalization is essential due to the diversity of learning profiles and the lack of face-to-face interaction. Besides the initial development of the generator programs, this study reports on the proposal of a methodology used to validate the quality of the generated texts and their adequacy to Kolb’s learning styles. The methodology was applied by six experts. The results show a high alignment of the texts with the Converging, Diverging, and Accommodating styles (100% on the Content Validity Index), with roo
m for improvement in the Assimilating style (83%). The research highlights the technical feasibility of the proposed approach, both from the perspective of generative AI and the methodology for certifying the quality of synthetically generated material.
(More)