Search
On-Site Program Calendar
Browse By Day
Browse By Time
Browse By Person
Browse By Room
Browse By Unit
Browse By Session Type
About AERA 2023 Annual Meeting
Program Information
Key Dates / FAQ
Search Tips
Change Preferences / Time Zone
Sign In
In this secondary data analysis study, we examined the source-based argumentative essays written by college developmental writers who participated in a strategy instruction intervention. We used natural language processing (NLP) tools to build models of writing quality with latent linguistic variables of academic language, connectives, global cohesion, source overlap, and syntactic complexity. CFA and SEM models indicated that academic language and global cohesion were significantly and positively associated with writing quality, while syntactic complexity was negatively associated with quality. Partial mediation effects were found for instructional condition on global cohesion with and without controlling for text length.