Revolutionizing Qualitative Human-Robot Interaction Research by Using GPT Models for Inductive Category Development
Year: 2024
Type: conference-paper
Abstract: Coding qualitative data is essential but time-consuming. This late-breaking report presents a new method for developing inductive categories utilizing GPT models. We examined two different GPT models (gpt-3.5-turbo-0125 and gpt-4o-2024-05-03) and three temperature settings (0, 0.5, 1), each with ten repetitions. The generated categories were fairly consistent across settings, although higher temperatures included less relevant aspects. The agreement for GPT-generated category assignments exceeded that of human coders, with the best performance observed at temperature setting 0. Thus, we recommend using a GPT model with the temperature setting 0 to create and assign inductive categories for qualitative data.
Authors: Arlinghaus, Clarissa Sabrina, Wulff, Charlotte, Maier, Günter W.
Institution: Bielefeld University
Language: English
Subfield: General Social Sciences
Field: Social Sciences
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W6930393078
FWCI:
Cites:
Cited by:
Related to: