Both student- and AI-text groups similarly affirmed contextual and character integration, with greater uncertainty in the ChatGPT-text group¶

Claim · All claims
Evidence · 1 study · causal r1 · q2
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? On Q14, 50% of the control group versus 47.62% of the experimental group affirmed the text reflected social and historical contextual elements; on Q15, character integration agreement was 59.09% versus 52.38%. → Andrea Roxana Bellot 2025

Evidence¶

Andrea Roxana Bellot 2025¶

Andrea Roxana Bellot, Mar Gutiérrez-Colón Plana, Katarzyna Agnieszka Baran. (2025). Redefining Literature Education: The Role of ChatGPT in Undergraduate Courses. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-025-00497-3

q2 · i? · causal · r1

Questionnaire items Q14 (Table 3) and Q15 (Table 4) asked both groups about integration of social/historical context and of original characters. The experimental group had higher "Maybe" rates (23.81% and 33.33%), which the authors read as a more critical or nuanced evaluation.

"In the control group, exactly half of the participants (50%) affirmed that the text successfully incorporates these contextual elements, suggesting a recognition of the text's ability to resonate with the original narrative's setting and background."

Discussion¶

Related Claims¶

• Students trusted the plot plausibility of peer-written alternative endings more than ChatGPT-generated endings — related
• Explicit contextualization instruction improves procedural aspects of historical writing without improving contextualization scores themselves — related
• Students rated ChatGPT-generated narrative endings equal to or higher than student-written endings on setting, themes, clarity of language and tone — related