Feedback Quality Analyser & Rewriter

Analyse existing written feedback for quality, specificity, actionability, and impact on student learning. Use when reviewing teacher or peer feedback to improve feedback practices.

What it does

Takes a piece of teacher or peer feedback, analyses it against Hattie & Timperley's (2007) four-level feedback model, and rewrites it to improve its level, specificity, and actionability. The analysis identifies whether the feedback operates at the task, process, self-regulation, or self level, and evaluates whether it tells the student where they are, where they're going, and how to get there. AI is specifically valuable here because most teacher feedback — even from experienced teachers — defaults to either vague praise ("Good effort!"), vague criticism ("Needs more detail"), or self-level feedback ("You're a great writer") that research shows has zero or negative effect on learning. Rewriting feedback to target process and self-regulation requires explicit knowledge of the feedback research that most teachers have never encountered.

The evidence behind it

Hattie & Timperley (2007) conducted a comprehensive meta-analysis finding that feedback has an average effect size of 0.73 — one of the highest in education research — but with enormous variability. Effective feedback answers three questions: Where am I going? (feed up), How am I going? (feed back), Where to next? (feed forward). They identified four feedback levels: task (correctness), process (strategies used), self-regulation (student's monitoring and control), and self (personal praise or criticism). Task-level feedback improves immediate performance; process-level feedback improves strategy use; self-regulation feedback builds independence. Self-level feedback ("You're so clever" / "Disappointing work") has no positive effect and can undermine learning by directing attention to ego rather than task. Kluger & DeNisi (1996) found that one-third of feedback interventions actually decreased performance — typically when feedback threatened self-esteem or directed attention away from the task. Wisniewski et al. (2020) updated the meta-analysis and confirmed that feedback containing information (specific, task-referenced) is significantly more effective than feedback containing only judgments (grades, praise, criticism). Shute (2008) identified that effective formative feedback is specific, timely, non-threatening, and focused on the gap between current and desired performance.

Sources

• Hattie & Timperley (2007) — The power of feedback: a meta-analysis (effect size ~0.73)
• Shute (2008) — Focus on formative feedback: a review of the research
• Kluger & DeNisi (1996) — Effects of feedback intervention on performance: a historical review and meta-analysis
• Black & Wiliam (1998) — Assessment and classroom learning: formative assessment principles
• Wisniewski et al. (2020) — The power of feedback revisited: a meta-analysis of educational feedback research

How to use it in your lesson

For the best results with EvidenceLesson, give it:

• feedback_text — The existing feedback to analyse (teacher-written or peer-written)
• task_context — What the student was asked to do and the learning objective
• student_work_summary (optional) — Brief summary of the student work the feedback refers to
• student_level (optional) — Age/year group and ability profile
• student_profiles (optional) — From context engine: self-regulation level, language proficiency, sensitivity factors
• rubric (optional) — From context engine: the rubric or success criteria used for this task

Known limitations

1. The rewrite requires knowing the actual student work. Without seeing Priya's essay, the rewritten feedback uses the quotation mentioned in the original and makes reasonable inferences about what she wrote. If the student work summary is provided, the rewrite will be more precise. Teachers should treat the rewrite as a model to adapt, not a final product.

1. Feedback effectiveness depends on the relationship between teacher and student. Wisniewski et al. (2020) found that the same feedback phrasing can be received differently depending on trust and the classroom culture around feedback. The rewrite assumes a supportive classroom environment. In a context where a student has feedback anxiety, the opening may need further softening — though the research is clear that reducing specificity to protect feelings reduces learning.

1. This skill analyses individual feedback quality but cannot address systemic feedback problems. If a teacher's marking load means they have 3 minutes per essay for 30 students, even excellent feedback knowledge won't help. Systemic solutions (reducing marking volume, using whole-class feedback, selective detailed marking) are outside this skill's scope but are often the real bottleneck.

Pairs well with