ChatGPT applications in academic writing: a review of potential, limitations, and ethical challenges

This article systematically reviewed 327 documents in the core collection of the Web of Science database regarding ChatGPT applications in the writing domain. This study aimed to comprehensively assess the latest progress and potential applications. ChatGPT demonstrates significant potential in overcoming writing anxiety, improving writing efficiency, generating initial scientific papers, and assisting researchers and students in giving feedback. However, it still faces significant challenges in data accuracy and the ethics of generated content, including inaccurate or outdated information, plagiarism risks, gender or race biases, etc. Authorship verification is particularly important for academic writing and publishing as it relates to objectivity, accuracy, and fairness. Future studies need to explore how to address these challenges through improvements atthe technical and policy levels, ensuringthat ChatGPT promotes the sustainable development and application of academic writing while adhering to ethical standards.