Research map / Large language models / AI and society
Democratizing Writing Support with AI: Insights from One Year of Real-World Interactions with an Open-Access Writing Feedback Tool
Babette Bühler, Ivo Bueno, Enkelejda Kasneci
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| revise text after AI feedback | PEER AI feedback tool · Revised texts (n=2,800) | overall judgment score: +0.067 (p < 0.001, r = 0.17) | Improved |
| revise text after AI feedback | PEER AI feedback tool · Revised texts | Headline score: +0.022 (p = 0.295) | No clear effect |
| revise after feedback | PEER AI feedback tool · Revised texts | Conclusion score: +0.138 | Improved |
| start from a low first draft (score 1-2) vs high (4-5) | PEER AI feedback tool · Revised texts | overall score change: 0.387 vs -0.035 | Improved |
| more revision rounds (1 to 4) | PEER AI feedback tool · Revised texts | overall score change: 0.049 -> 0.198 | Improved |
| fifth revision round vs fourth | PEER AI feedback tool · Revised texts | overall score change: 0.198 -> 0.135 (p = 0.090) | No clear effect |
| larger textual edits between drafts | PEER AI feedback tool · Revised texts | score improvement: Pearson r = −0.020 | No clear effect |
| mention a criterion in the feedback recommendations | PEER AI feedback tool · Revised texts | next-draft improvement on that criterion: 25.3% (Conclusion) vs 10.7% (Linguistic style req.) | Mixed |
| academic secondary vs lower secondary school | PEER AI feedback tool · Revised texts | overall score change: 0.083 vs 0.034 | Improved |
Closest papers by meaning
- From Consumers to Critical Users: Prompty, an AI Literacy Tool for High School Students (AAAI 2024 · similarity 0.89)
- AAAR-1.0: Assessing AI’s Potential to Assist Research (ICML 2025 · similarity 0.87)
- Scaling Equitable Reflection Assessment in Education via Large Language Models and Role-Based Feedback Agents (AAAI 2026 · similarity 0.87)
- Quality-Diversity through AI Feedback (ICLR 2024 · similarity 0.87)
- Towards Automatic Boundary Detection for Human-AI Collaborative Hybrid Essay in Education (AAAI 2024 · similarity 0.86)
- Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews (ICML 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
