Affiliation:
1. Faculty of Chinese Medicine Science Guangxi University of Chinese Medicine , Nanning , Guangxi , , China .
Abstract
Abstract
The emergence of the ChatGPT language model has sparked significant interest in educational circles, thanks to its capabilities in generating text, understanding context, and engaging in logical reasoning and conversation. This study explores the impact of ChatGPT on English writing, integrating statistical language models and TF-IDF word frequency analysis to develop a method for identifying and scoring deviations in English essays. Our findings demonstrate the model’s high accuracy in detecting digressions across three categories (88%, 73.33%, and 60%), and its scoring closely aligns with human assessments, with a mean error of just 5.17 and a Pearson correlation coefficient of 0.8024. This evidence supports the model’s reliability and significant potential for application in English writing evaluation.
Reference18 articles.
1. Bai, B., & Guo, W. (2021). Motivation and self-regulated strategy use: relationships to primary school students’ english writing in hong kong:. Language Teaching Research, 25(3), 378-399.
2. Fatima, Q., & Akbar, R. A. (2018). Teaching practices used for developing english writing skill at secondary level. The Journal of Educational Research, 21.
3. Olson, C. B., Matuchniak, T., Chung, H. Q., Stumpf, R., & Farkas, G. (2017). Reducing achievement gaps in academic writing for latinos and english learners in grades. Journal of Educational Psychology, 109(1), págs. 1-12.
4. Chew, C. S., Idris, N., Loh, E. F., Wenhi Vivian Wu, & Bimba, A. T. (2019). The effects of a theory-based summary writing tool on students’ summary writing. Journal of Computer Assisted Learning, 35(1).
5. Yu, S., & Jiang, L. (2021). L2 university students’ motivational self system in english writing: a sociocultural inquiry. Applied Linguistics Review.