Abstract and Keywords
Rapid technological advances in natural language processing over the past ten years have made it possible for computer systems to evaluate student essays in high-stakes testing, as well as low-stakes writing practice environments. This article describes some of the linguistic and computational bases for automated essay evaluation. Computer systems have been developed for holistic scoring and for the generation of diagnostic feedback. For holistic scoring, a reader assigns a single numerical score to the quality of writing in an essay. For diagnostic feedback, a reader identifies features in writing. When people rate essays, they are instructed to follow a set of scoring criteria that characterize different aspects underlying the writing construct. Specifically, these are the aspects that can be measured in a writing task. For expository writing tasks, for instance, readers are typically instructed to focus on a number of features in writing that contribute to a high-quality essay.
Oxford Handbooks Online requires a subscription or purchase to access the full text of titles within the service. Public users can however freely search the site and view restricted versions of this content, plus any full text content that is freely available.
If you think you should have access to this title, please contact your librarian.
To troubleshoot, please check our FAQs, and if you can't find the answer there, please contact us .