Automated Formative Writing Assessment Using a Levels of Language Framework
Wilson, J., Roscoe, R. D., & Ahmed, Y. (2017). Automated formative writing assessment using a levels of language framework. Assessing Writing, 34, 16-36. https://doi.org/10.1016/j.asw.2017.08.002
This study tests whether automated Coh-Metrix measures can represent three levels of language in student writing - word choice, syntax, and cohesion/discourse - and whether those latent factors predict performance on state writing assessments for grades 6 and 8.
Key takeaways
- A subset of nine Coh-Metrix measures fit a three-factor levels-of-language model at both grade levels.
- The latent discourse factor predicted the direct assessment of writing.
- The latent discourse and sentence factors predicted the editing and revising test.
- The findings provide a proof of concept for automated formative writing assessment.
- The study suggests a path toward integrating levels-of-language detection into automated writing evaluation and teacher feedback systems.
Why it matters
This article advanced Dr. Wilson's scholarship by linking automated assessment to a theory-driven levels-of-language framework, expanding AWE beyond simple scoring toward more diagnostic formative use.
Coauthors
Joshua Wilson, Rod D. Roscoe, Yusra Ahmed
Topic tags
External links