METHODOLOGICAL PRINCIPLES OF DEVELOPING A NATIONAL LEARNER ERROR CORPUS FOR AUTOMATED ESSAY SCORING SYSTEMS IN UZBEKISTAN

Authors

  • Kholbutaeva Pokiza Master’s Student of Webster University in Tashkent

Keywords:

learner error corpus, automated essay scoring, natural language processing, language assessment, corpus linguistics, Uzbekistan, educational technology, error annotation.

Abstract

Abstract. The development of automated essay scoring systems requires reliable linguistic resources that reflect the actual writing patterns of language learners. However, automated assessment tools trained primarily on international datasets may fail to identify language-specific errors and contextual features characteristic of learners in Uzbekistan. This thesis examines the methodological principles for developing a national learner error corpus to support automated essay scoring in Uzbek educational contexts. The proposed framework focuses on representative data collection, learner proficiency classification, systematic error annotation, linguistic diversity, ethical data management, and corpus validation. Particular attention is given to recurring grammatical, lexical, orthographic, and discourse-level errors in English essays written by Uzbek learners. The study proposes an annotation framework that combines expert linguistic judgment with computational processing. Establishing such a corpus could improve the reliability, contextual relevance, and educational usefulness of automated essay scoring systems while supporting the development of locally adapted language assessment technologies.

References

1. Attali, Y., & Burstein, J. (2006). Automated essay scoring with e-rater® V.2. The Journal of Technology, Learning and Assessment, 4(3).

2. Burstein, J., Tetreault, J., & Madnani, N. (2013). The e-rater® automated essay scoring system. In The Handbook of Automated Essay Evaluation (pp. 55–67). Routledge.

3. Corder, S. P. (1967). The significance of learners’ errors. International Review of Applied Linguistics in Language Teaching, 5(4), 161–170.

4. Granger, S. (2003). Error-tagged learner corpora and CALL: A promising synergy. CALICO Journal, 20(3), 465–480.

Downloads

Published

2026-09-25

How to Cite

Kholbutaeva Pokiza. (2026). METHODOLOGICAL PRINCIPLES OF DEVELOPING A NATIONAL LEARNER ERROR CORPUS FOR AUTOMATED ESSAY SCORING SYSTEMS IN UZBEKISTAN. NEW APPROACHES IN EDUCATION: PEDAGOGY, INNOVATION, AND DEVELOPMENT, 2(09), 260–264. Retrieved from https://worldconferences.us/index.php/nae/article/view/1740