Motivation prompts shift feedback tone: unmotivated students receive enthusiastic, collaborative encouragement while motivated students receive direct, higher-level critique¶

Claim · All claims
Evidence · 1 study · causal r2 · q2
Currency · no dated study recorded · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Feedback for students identified as unmotivated adopted an encouraging, collaborative tone with inclusive language and positive reinforcement, whereas feedback for motivated students focused on precision and refinement with constructive criticism. → Tan et al. 2026

Evidence¶

Tan et al. 2026¶

Mei Tan, Lena Phalen, and Dorottya Demszky. 2026. Marked Pedagogies: Examining Linguistic Biases in Personalized Automated Writing Feedback. In LAK 2026: 16th International Learning Analytics and Knowledge Conference (LAK 2026). ACM, New York, NY, USA. doi:10.1145/3785022.3785113

q2 · i? · causal · r2

Lexical comparison of unmotivated- versus motivated-prompted feedback for the same essays (Table 5: let's, try, great, love versus enhance, rephrase, strengthen, clarify), with representative comments from GPT-4o, GPT-3.5, and Llama-3.3 70B. No effect size is printed for the qualitative pattern.

"Feedback for students identified as unmotivated often adopted an encourag- ing and collaborative tone, using inclusive language and upbeat prompts"

Discussion¶

Learner Variables¶

• Motivation — moderator: an instructional effect differs with it

Related Claims¶

• Gender prompts shift feedback stance: female students receive affective, first-person, empathy-oriented feedback while male students receive objective, task-oriented critique — related
• LLM feedback for students marked by race, language, disability, gender, or motivation shows positive feedback bias and feedback withholding bias — more praise and less substantive critique than for unmarked counterparts — a broader claim this one bears on
• LLM feedback sentiment tracks assigned scores: low scores come with more criticism, high scores with more praise — related
• Explicitly prompting a student attribute produces large, systematic increases in the concentration of stereotype-aligned marked words in LLM-generated writing feedback — related
• The LLM evaluator score discriminates between simulated-student motivation profiles — related