Analyzing Language Skills in Persuasive Writing and AI-Generated Feedback Using Factor Analysis Methods

• In Event: AERA Roundtable Session Sunday 7:45 am - Gold 3
  In Roundtable Session: Exploring the Impact of AI and Technology on Literacy Instruction

Abstract

This project investigates the development of persuasive writing skills among secondary students. Student-constructed essays are valuable for assessing higher-order thinking but pose challenges in evaluation due to complexity and potential bias. The study has two goals: (1) to identify key features influencing essay quality using product-oriented measures of micro- and macrostructural writing dimensions, and to establish a latent factor structure with tested measurement invariance across special education status; and (2) to design and implement GPT-based automated feedback prompts informed by these findings. Results highlight the potential of using factor-analytic models to guide AI-driven scoring and feedback, supporting personalized instruction and promoting educational equity by enhancing writing proficiency through adaptive, context-aware feedback mechanisms.

Author

• Heqiao Wang, Old Dominion University