Examining University Students’ Engagement with ChatGPT in English Essay Writing: Interaction Patterns and Perceptions

Abstract This study examines the interaction patterns and perceptions of university students who used ChatGPT during the English essay writing process. Twenty university students in Korea were divided into two groups based on English proficiency: 10 advanced learners and 10 intermediate learners. Participants completed essay writing with the assistance of ChatGPT, and their interaction logs were collected throughout the process. The logs were analyzed using Epistemic Network Analysis (ENA) to identify interaction patterns across proficiency levels. In addition, thematic analysis of interview data was conducted to examine learners' perceptions of ChatGPT-supported writing. ENA results showed that advanced learners used ChatGPT primarily during the prewriting stage for information gathering, word choice exploration, and translation, and later shifted to refining expressions during drafting. In contrast, intermediate learners relied more heavily on ChatGPT during drafting, particularly for lexical and syntactic exploration. Thematic analysis revealed that although learners recognized ChatGPT as an efficient and supportive tool for English essay writing, they also noted its limitations, including unclear information sources and insufficient contextual understanding.

Authors

Institutions

Publication Details

Journal
The Asia-Pacific Education Researcher
Published
2026-02-04
DOI
https://doi.org/10.1007/s40299-025-01076-9
Citations
1
Primary Topic
Artificial Intelligence in Healthcare and Education
Type
article
Field-Weighted Citation Impact
17.70
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Examining University Students’ Engagement with ChatGPT in English Essay Writing: Interaction Patterns and Perceptions

Hyeji Jang, Jin Liu, Hyo Jeong So
1 citations
The Asia-Pacific Education Researcher
Artificial Intelligence in Healthcare and Education
17.70
article

Examining University Students’ Engagement with ChatGPT in English Essay Writing: Interaction Patterns and Perceptions

Hyeji Jang, Jin Liu, Hyo Jeong So
article en
1 citations

Abstract

Abstract This study examines the interaction patterns and perceptions of university students who used ChatGPT during the English essay writing process. Twenty university students in Korea were divided into two groups based on English proficiency: 10 advanced learners and 10 intermediate learners. Participants completed essay writing with the assistance of ChatGPT, and their interaction logs were collected throughout the process. The logs were analyzed using Epistemic Network Analysis (ENA) to identify interaction patterns across proficiency levels. In addition, thematic analysis of interview data was conducted to examine learners' perceptions of ChatGPT-supported writing. ENA results showed that advanced learners used ChatGPT primarily during the prewriting stage for information gathering, word choice exploration, and translation, and later shifted to refining expressions during drafting. In contrast, intermediate learners relied more heavily on ChatGPT during drafting, particularly for lexical and syntactic exploration. Thematic analysis revealed that although learners recognized ChatGPT as an efficient and supportive tool for English essay writing, they also noted its limitations, including unclear information sources and insufficient contextual understanding.

The Asia-Pacific Education Researcher
Ewha Womans University (KR)
Quality Education
Openalex Percentile: Top 2%
Artificial Intelligence in Healthcare and Education
17.70
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.