Abstract
This study assessed how ChatGPT as a debate simulator affected learning and critical application of international relations theories among 72 undergraduate students from the Colombian Caribbean. Using a quasi-experimental design, the research compared free simulation, guided simulation, and synchronous feedback approaches. Statistical analysis through t-tests, ANOVA, and ordinal logistic regression showed that guided simulation produced the strongest improvements in theoretical understanding, especially for dependency and postcolonial frameworks. Students from the Caribbean region showed enhanced ability to apply theories to regional contexts after AI-mediated debates. The findings suggest that structured AI-mediated debates help students connect abstract theoretical concepts with concrete geopolitical analyses, particularly when examining peripheral countries’ positions in the global system.
Keywords
Get full access to this article
View all access options for this article.
References
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
