Paper Summary
Share...

Direct link:

Leveraging Large Language Models to Fostering Young Students' Metacognition of Revision

Thu, April 24, 9:50 to 11:20am MDT (9:50 to 11:20am MDT), The Colorado Convention Center, Floor: Terrace Level, Bluebird Ballroom Room 3B

Abstract

Although effective revision is a crucial component of writing instruction, few automated writing evaluation (AWE) systems specifically focus on the quality of the revisions students undertake. This study investigates the potential of large language models (ChatGPT) for providing feedback that builds students' metacognition of revision by highlighting the revision actions implemented in their essays. Results show that ChatGPT had significant potential to accurately detect students’ revision efforts and diagnose the effectiveness of implemented revision strategies. However, the quality of the suggestions for further improving essays varies based on the revision goals. The implications for improving AWE systems focusing on young students will be discussed.

Authors