Abstract

Objectives: This research aims to analyze and evaluate the content generated by ChatGPT technology regarding the use of this tool by graduate students in assessment processes. It also seeks to identify the extent to which these technologies can provide accurate and unbiased analysis, understand how ChatGPT processes information provided to stakeholders, and identify the differences and similarities in ChatGPT’ s responses when dealing with the same information and data provided to it at different times. Methodology: A qualitative research approach was adopted using a qualitative content analysis of the responses provided by the ChatGPT technology. The researcher directed basic standardized questions - using the same wording - about the criteria for creating a good introduction to scientific research, through the responses of four students with three attempts at different times. Thus, the questions were directed to the ChatGPT tool, resulting in 12 responses for each topic, for a total of 24 responses. Results: The results indicated that ChatGPT responses provide similar content in answers about recurring topics on the same question at different times, but the differences appear in the details, phrasing, sentence structure, and choice of words, while keeping the basic content constant. The results also indicated that ChatGPT can provide some differences that are specifically modified when other clarifying questions are asked. On the other hand, the results showed that the researcher's introduction prepared without using the ChatGPT tool is more accurate and comprehensive in the elements and criteria of a good scientific introduction, while ChatGPT responses are considered the gateway that enables the exploration and immersion of main ideas. Conclusion: The researcher recommends the necessity of

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call