ChatGPT produced more descriptive feedback than peers on argumentative essays¶

Claim · All claims
Evidence · 1 study · causal r1 · q2 · i1 small
Currency · newest study 2024 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i1 ChatGPT feedback scored higher than peer feedback on the description component of feedback quality. → Banihashem 2024

Evidence¶

Banihashem 2024¶

Banihashem, S. K., Taghizadeh Kerman, N., Noroozi, O., Moon, J., & Drachsler, H. (2024). Feedback sources in essay writing: peer-generated or AI-generated feedback? International Journal of Educational Technology in Higher Education. https://doi.org/10.1186/s41239-024-00455-4

q2 · i1 · causal · r1

MANCOVA result for the description component of the feedback coding scheme (Table 1): peer mean 1.91 (SD 0.29) versus ChatGPT mean 2.00 (SD 0.00), F (1, 146) = 3.25, p < 0.05, η2 = 0.03, a small effect. The article notes ChatGPT "tended to produce more extensive descriptive feedback".

"Cognitive Description Peer feedback 1.91 0.29 F (1, 146) = 3.25, p < 0.05*, η2 = 0.03"

Discussion¶

Related Claims¶

• Peers outperformed ChatGPT in identifying problems within essays — related
• Essay quality correlates positively with the affective feature of ChatGPT feedback and negatively with the affective feature of peer feedback — related
• No significant relationship exists between essay quality and the overall quality of feedback generated by peers and ChatGPT — related