Classification accuracy and efficiency of writing screening using automated essay scoring
Wilson, J., & Rodrigues, J. (2020). Classification accuracy and efficiency of writing screening using automated essay scoring. Journal of School Psychology, 82, 123-140. https://doi.org/10.1016/j.jsp.2020.08.008
This study tested whether automated essay scoring could support universal screening for writing by classifying elementary students as at risk for later English language arts failure. It compared a multi-prompt automated essay scoring screener, shorter automated essay scoring versions with fewer prompts, and word-count scoring using ROC-based classification accuracy analyses.
Key takeaways
- Automated essay scoring-based writing screeners showed acceptable classification accuracy for identifying students at risk.
- Shorter screener versions with fewer prompts remained efficient while retaining useful accuracy.
- Automated essay scoring outperformed screeners scored only for word count.
Why it matters
Provides a proof of concept for using automated essay scoring as an efficient writing screener in universal screening contexts.
Coauthors
Joshua Wilson, Jessica Rodrigues
Topic tags
External links