Session Summary
Share...

Direct link:

Building Theory-Informed and Context-Sensitive Natural Language Processing to Capture Self-Regulated Learning in Action

Thu, April 24, 5:25 to 6:55pm MDT (5:25 to 6:55pm MDT), The Colorado Convention Center, Floor: Terrace Level, Bluebird Ballroom Room 2B

Session Type: Symposium

Abstract

In this symposium, we present five projects that leverage natural language processing (NLP) to inform self-regulated learning (SRL) theory and provide models for using these methods to analyze student language in authentic learning contexts. Using SRL frameworks as an anchoring theoretical lens, we demonstrate how NLPs contribute to theory refinement and application by training large language models (LLMs), engineering prompts to produce feedback with AI, using AI to explore the language in think-aloud protocol codes, investigating student reporting with sentiment analysis, and using dictionary-based methods to investigate diverse student language-use. We close the session with a consideration of the inclusivity of NLP methods and ways to mitigate bias and appreciate all students' voices as they describe their learning processes.

Sub Unit

Chairs

Papers

Discussant