Djebar, Ahmed HoussamBOURI, Hadj2020-11-292020-11-292020http://hdl.handle.net/123456789/9459ndices classified under the three banks of the linguistic features in question were chosen. After statistical analysis of the data, results have shown that lexical diversity and syntactic complexity successfully differentiate between highly and poorly students' writings. While lexical diversity was found to be the best predictor of assessors' ratings. These findings point out, on the one hand, the need to incorporate linguistic features as a pivotal element in writing instruction for students, and on the other hand, as an independent element in writing assessment for teachers. Hereafter, limitations were stated and suggestions for future research were proposed.enWriting qualityLinguistic featureAutomated writing evaluation