Evaluating literature reviews conducted by humans versus chatgpt: comparative study

HIGHLIGHTS

• What: The aim of this study is to conduct a literature review using OpenAI`s ChatGPT-4 model ("GPT4") and then conduct a comparative analysis against a review conducted by human researchers. In the review conducted by researchers, all the identified factors are considered quite relevant to the subject matter and their relevance is supported by scientific evidence. Breadth and depth of knowledge the experiments demonstrated a considerable breadth of knowledge within the GPT-4 model, significantly surpassing that of human researchers. Limitations and future research the study has some limitations.
• Who: Mostafapour et al . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.