Author(s) Piers Howe (The University of Melbourne) - pdhowe@unimelb.edu.au
Pre-registered on 07/24/2023 11:20 PM (PT)
1) Have any data been collected for this study already? No, no data have been collected for this study yet.
2) What's the main question being asked or hypothesis being tested in this study? Whether people think that the answer provided by Chat GPT is better than the one provided by a human.
3) Describe the key dependent variable(s) specifying how they will be measured. Participants will be presented with two answers and asked which one is a) more balanced, b) more complete, c) more empathetic, d) more helpful, and e) better. They will also be asked which one they think is written by a computer and whether they would prefer their questions to be answered by a human or by a computer.
4) How many and which conditions will participants be assigned to? One condition.
5) Specify exactly which analyses you will conduct to examine the main question/hypothesis. The above seven questions have binary answers. For each question, we will perform a binomial test to determine whether one answer is selected more than the other.
6) Describe exactly how outliers will be defined and handled, and your precise rule(s) for excluding observations. No observations will be excluded.
7) How many observations will be collected or what will determine sample size? No need to justify decision, but be precise about exactly how the number will be determined. We will run 400 participants.
8) Anything else you would like to pre-register? (e.g., secondary analyses, variables collected for exploratory purposes, unusual analyses planned?) Participants will be recruited from a pool of MTurk workers that has been pre-screened to remove potential bots.
