An artificial intelligence (AI) model can score English essays with improved accuracy across different writing topics, according to work published in the International Journal of Continuing Engineering Education and Life-Long Learning. The tool could help schools assess student work more efficiently while reducing inconsistencies in marking.
The system, known as DTS-Score, combines several machine-learning techniques to analyse the meaning and structure of essays, including their paragraph organisation. In tests, it achieved a weighted kappa coefficient of 0.866. This is a measure of agreement between scoring outcomes, where 1.000 would represent a perfect output. A further development might allow the accuracy of the system to be compared with marking undertaken by teachers themselves.
The researchers developed the model to address a common problem in automated essay assessment. That is, systems trained on one essay topic may perform less reliably when evaluating writing on another subject. Their approach uses transfer learning, a technique that allows a model to apply knowledge acquired from one task to a different but related one. In large educational establishments, such a system could help process substantial volumes of student essays, flagging those that appear to stray from the assigned topic and allowing teachers to focus their attention on writing that may require closer scrutiny.
Chen, H. (2026) ‘Intelligent English composition scoring method based on transfer paragraph segmentation and Pearson detection’, Int. J. Continuing Engineering Education and Life-Long Learning, Vol. 36, No. 13, pp.1–25.
News media may use this press release as source material, in whole or in part, provided the content is not materially misrepresented. A link back to the original article is appreciated.
No comments:
Post a Comment