Exploring ChatGPT's Ability to Classify the Structure of Literature Reviews in Engineering Research Articles

ChatGPT is a newly emerging artificial intelligence (AI) tool that can generate and assess written text. In this study, we aim to examine the extent to which it can correctly identify the structure of literature review sections in engineering research articles. For this purpose, we conducted a manual content analysis by classifying paragraphs of literature review sections into their corresponding categories that are based on Kwan's model, which is a labeling scheme for structuring literature reviews. We then asked ChatGPT to perform the same categorization and compared both outcomes. Numerical results do not imply a satisfactory performance of ChatGPT; therefore, writers cannot fully depend on it to edit their literature reviews. However, the AI chatbot displays an understanding of the given prompt and is able to respond beyond the classification task by giving supportive and useful explanations for the users. Such findings can be especially helpful for beginners who usually struggle to write comprehensive literature review sections since they highlight how users can benefit from this AI chatbot to revise their drafts at the level of content and organization. With further investigations and advancement, AI chatbots can also be used for teaching proper literature review writing and editing.