Exploring the efficacy of ChatGPT-based feedback compared with teacher feedback and self-feedback : evidence from Chinese-English translation

Abstract

ChatGPT, a cutting-edge AI-powered Chatbot, can quickly generate responses to given commands. While ChatGPT was reported to have the capacity to deliver useful feedback, it is still unclear about its effectiveness compared with conventional feedback approaches, such as self-feedback (SF) and teacher feedback (TF). To address this issue, this study compared the revised Chinese to English translation texts produced by 45 Chinese Master of Translation and Interpretation (MTI) students, who learned English as a Second Language (ESL), based on three feedback types (i.e., SF, TF, and ChatGPT feedback). The data was analyzed using BLEU score to gauge the overall translation quality as well as Coh-Metrix to examine linguistic features across three dimensions: lexicon, syntax, and cohesion. The findings revealed that SF and TF-guided translation texts surpassed those with ChatGPT feedback, as indicated by the BLEU score. In terms of linguistic features, ChatGPT feedback demonstrated superiority, particularly in enhancing lexical capability and referential cohesion in the translation texts. However, SF and TF proved more effective in developing syntax-related skills, as they addressed instances of incorrect usage of the passive voice. These diverse outcomes indicate ChatGPT’s potential as a supplementary resource, complementing traditional teacher-led methods in translation practice.