EFFECTS OF AI-GENERATED FEEDBACK ON LEXICAL DIVERSITY IN L2 STUDENT ESSAYS

Read full text Summarise with VIRAT
Authors: Jasmina Ashirova, Wordly Knowledge Publishing Centre
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This study investigates the effects of AI-generated feedback on lexical diversity in second language (L2) student essays. With the increasing integration of artificial intelligence tools into language education, automated feedback systems are becoming widely used to support student writing. This research focuses on how such feedback influences students’ vocabulary use, particularly lexical variation and avoidance of repetition in academic writing. The study employs a quasi-experimental design involving L2 university students who were divided into two groups. The experimental group received AI-generated feedback on their essay drafts, while the control group received traditional teacher feedback. Lexical diversity was measured using indicators such as type–token ratio and lexical variation indices. A mixed-methods approach was applied, combining quantitative analysis of students’ written texts with qualitative examination of revision patterns. The findings indicate that students who received AI-generated feedback demonstrated a noticeable improvement in lexical diversity compared to those who received only teacher feedback. AI feedback encouraged the use of synonyms, more precise word choices, and greater awareness of lexical repetition. However, the results also suggest that AI feedback is most effective when used as a complementary tool rather than a replacement for human instruction. The study concludes that AI-generated feedback can positively contribute to lexical development in L2 writing when integrated thoughtfully into the learning process.

Fields of Study & Subjects

Second Language Acquisition and Learning EFL/ESL Teaching and Learning English Language Learning and Teaching

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
21 March 2026
Language
EN
Document type
Dataset