Comparing the key lexico-grammatical features of research papers and reports by ChatGPT and EFL students

Generative Artificial Intelligence technologies such as ChatGPT have shown great potential in facilitating better teaching and learning experiences in the EFL context. While the literature posits that ChatGPT can generate naturalistic human-like language when prompted, it remains unclear the extent to which it can simulate the lexico-grammatical choices of human writing, given real-life situational contexts. The present study draws on key feature analysis to identify and compare the pervasive lexico-grammatical features of AI-generated academic essays to student-authored ones.