Abstract
We develop models to classify desirable evidence and desirable reasoning revisions in student argumentative writing. We explore two ways to improve classifier performance – using the essay context of the revision, and using the feedback students received before the revision. We perform both intrinsic and extrinsic evaluation for each of our models and report a qualitative analysis. Our results show that while a model using feedback information improves over a baseline model, models utilizing context - either alone or with feedback - are the most successful in identifying desirable revisions.- Anthology ID:
- 2023.findings-eacl.193
- Volume:
- Findings of the Association for Computational Linguistics: EACL 2023
- Month:
- May
- Year:
- 2023
- Address:
- Dubrovnik, Croatia
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2550–2561
- Language:
- URL:
- https://aclanthology.org/2023.findings-eacl.193
- DOI:
- Cite (ACL):
- Tazin Afrin and Diane Litman. 2023. Predicting Desirable Revisions of Evidence and Reasoning in Argumentative Writing. In Findings of the Association for Computational Linguistics: EACL 2023, pages 2550–2561, Dubrovnik, Croatia. Association for Computational Linguistics.
- Cite (Informal):
- Predicting Desirable Revisions of Evidence and Reasoning in Argumentative Writing (Afrin & Litman, Findings 2023)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2023.findings-eacl.193.pdf