Integrate ChatGPT as a feedback resource alongside peer feedback for essay writing in higher education¶

Strategy · All strategies
Evidence · 7 claims (6 for, 1 mixed) · 4 studies (1 causal, 1 associational, 1 qualitative, 1 design), q2 · 1 of 4 report an effect size · 7 claims rest on one study

Description¶

The article recommends combining ChatGPT-generated and peer-generated feedback for argumentative essay tasks in higher education, since the two sources show complementary strengths: ChatGPT provides extensive descriptive feedback while peers excel at identifying problems. The authors argue this combination "creates a synergistic relationship that could result in better feedback outcomes" and could alleviate teacher workload in large online courses.

Design Implications¶

Context¶

Requirements¶

• Access to ChatGPT and a peer feedback process using the same feedback prompt for both sources

Constraints¶

• The study did not investigate whether students actually utilize the feedback or whether essays improve in revision
• ChatGPT is sensitive to prompt wording, so prompt-related factors should be controlled
• ChatGPT can potentially generate inaccurate results

Target Learners¶

• graduate students in higher education

Target Learning Goals¶

• argumentative essay writing skills
• giving and receiving quality feedback

Claims¶

• ChatGPT produced more descriptive feedback than peers on argumentative essays [+W]
• Essay quality correlates positively with the affective feature of ChatGPT feedback and negatively with the affective feature of peer feedback [+W]
• No significant relationship exists between essay quality and the overall quality of feedback generated by peers and ChatGPT [~W]
• Peers outperformed ChatGPT in identifying problems within essays [+W]
• Students perceived peer group feedback as contextually rich but sometimes subjective, and ChatGPT-4o feedback as more objective and well structured but occasionally lacking contextual sensitivity [+W]
• Business Writing students valued AI feedback for higher-order and sentence-level comments but found it sometimes too general, while appreciating peers' contextual knowledge [+W]
• First-year EAP students prefer a hybrid feedback model combining AI-generated comments with instructor feedback over either source alone [+W]

Related Strategies¶

• Combine AI-based feedback on early drafts with human feedback on later drafts, and teach students to evaluate AI feedback critically
• Use hybrid human–AI feedback models that combine AI's and instructors' complementary strengths
• Have students compare their peer-feedback revisions with AI-generated revisions to examine dialogic positioning

Examples¶

-

Key Sources¶

• 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