Table 1.
The mean (SD) of the reviewers’ evaluation of the research stages of each version of the ChatGPT-generated research studies.
| Descriptive and research | Mean (SD) | ||
| Abstract |
|
||
|
|
Version 1 | 7.04 (0.71) | |
|
|
Version 2 | 7.26 (0.62) | |
|
|
Version 3 | 7.48 (0.51) | |
|
|
Version 4 | 7.57 (0.51) | |
|
|
Total | 7.34 (0.62) | |
| Research idea |
|
||
|
|
Version 1 | 6.30 (0.35) | |
|
|
Version 2 | 6.51 (0.40) | |
|
|
Version 3 | 6.47 (0.38) | |
|
|
Version 4 | 6.85 (0.33) | |
|
|
Total | 6.53 (0.41) | |
| Literature review |
|
||
|
|
Version 1 | 5.88 (0.36) | |
|
|
Version 2 | 6.43 (0.61) | |
|
|
Version 3 | 6.80 (0.57) | |
|
|
Version 4 | 7.32 (0.37) | |
|
|
Total | 6.61 (0.71) | |
| Methodology |
|
||
|
|
Version 1 | 5.59 (0.49) | |
|
|
Version 2 | 6.02 (0.51) | |
|
|
Version 3 | 6.61 (0.54) | |
|
|
Version 4 | 6.93 (0.53) | |
|
|
Total | 6.29 (0.73) | |
| Citation and references |
|
||
|
|
Version 1 | 4.74 (0.54) | |
|
|
Version 2 | 5.00 (0.50) | |
|
|
Version 3 | 5.41 (0.54) | |
|
|
Version 4 | 5.61 (0.69) | |
|
|
Total | 5.19 (0.66) | |
| Plagiarism |
|
||
|
|
Version 1 | 6.67 (0.36) | |
|
|
Version 2 | 6.78 (0.36) | |
|
|
Version 3 | 7.46 (0.30) | |
|
|
Version 4 | 7.83 (0.42) | |
|
|
Total | 7.18 (0.60) | |
| Total |
|
||
|
|
Version 1 | 6.01 (0.12) | |
|
|
Version 2 | 6.32 (0.28) | |
|
|
Version 3 | 6.61 (0.23) | |
|
|
Version 4 | 6.97 (0.23) | |
|
|
Total | 6.48 (0.42) | |
| Overall qualitya |
|
||
|
|
Version 1 | 5.13 | |
|
|
Version 2 | 5.8 | |
|
|
Version 3 | 6.25 | |
|
|
Version 4 | 7.08 | |
aOnly means were compared.