%0 Generic
%A Tabone, Wilbert
%A de Winter, Joost
%D 2023
%T Supplementary materials for the article: Using ChatGPT for Human Computer Interaction Research: A Primer
%U https://data.4tu.nl/articles/dataset/_/21916017
%R 10.4121/21916017.v1
%K ChatGPT
%K qualitative research method
%K think-aloud protocols
%K questionnaire data
%K thematic-analysis
%K augmented reality
%K prompt engineering
%K artificial intelligence
%X <p>Supplementary data for the paperTabone, W., &amp; De Winter, J. C. F. (2023). Using ChatGPT for Human–Computer Interaction Research: A Primer. Royal Society Open Science, 10, 231053.</p><p><br></p><p>This repository contains MATLAB scripts (tested in MATLAB R2023a),&nbsp;</p><p>input data (source data read by the MATLAB scripts),&nbsp;</p><p>and saved ChatGPT outputs for Study 1, 2, and 3 of the following research paper:</p><p><br></p><p>- Study1.m contains code for 2 different prompts, as well as different batch sizes (25 vs. 992), as described in the paper.</p><p>- Study1_bootstrapping.m contains the code for the bootstrapping approach, also described in the paper.</p><p>- Study1_randomness_test.m contains the code corresponding to the systematic variation of the temperature parameter described in the paper.</p><p>- Study2.m contains the code that corresponds to the interview summary for the Virtual fence augmented reality (AR) interface.</p><p>- Study2_16k_test.m contains the code of a trial, in which the entire interview was submitted all at once; something that has recently become possible with the 16k variant of the GPT-3.5 (not described in the paper)</p><p>- Study2_content_analysis.m and Study2_content_analysis_16k contain code for attempts at letting GPT perform a content analysis of the interview (described in the discussion of the paper).</p><p>- Study2_gpt4.m is similar to Study2.m but now adopts GPT-4 instead of GPT-3.5</p><p>- Study3_bootstrapping.m is code for the bootstrapping approach of the transcripts, as described in the paper.</p>
%I 4TU.ResearchData