Revolutionizing Qualitative Human-Robot Interaction Research by Using GPT Models for Inductive Category Development
Arlinghaus CS, Wulff C, Maier GW (2024)
Presented at the The 33rd IEEE International Conference on Robot and Human Interactive Communication (IEEE RO-MAN 2024), Pasadena.
Konferenzbeitrag | Englisch
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Autor*in
Abstract / Bemerkung
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.
Erscheinungsjahr
2024
Konferenz
The 33rd IEEE International Conference on Robot and Human Interactive Communication (IEEE RO-MAN 2024)
Konferenzort
Pasadena
Konferenzdatum
2024-08-26 – 2024-08-30
Page URI
https://pub.uni-bielefeld.de/record/2993494
Zitieren
Arlinghaus CS, Wulff C, Maier GW. Revolutionizing Qualitative Human-Robot Interaction Research by Using GPT Models for Inductive Category Development. Presented at the The 33rd IEEE International Conference on Robot and Human Interactive Communication (IEEE RO-MAN 2024), Pasadena.
Arlinghaus, C. S., Wulff, C., & Maier, G. W. (2024). Revolutionizing Qualitative Human-Robot Interaction Research by Using GPT Models for Inductive Category Development. Presented at the The 33rd IEEE International Conference on Robot and Human Interactive Communication (IEEE RO-MAN 2024), Pasadena. https://doi.org/10.5281/zenodo.13693979
Arlinghaus, Clarissa Sabrina, Wulff, Charlotte, and Maier, Günter W. 2024. “Revolutionizing Qualitative Human-Robot Interaction Research by Using GPT Models for Inductive Category Development”. Presented at the The 33rd IEEE International Conference on Robot and Human Interactive Communication (IEEE RO-MAN 2024), Pasadena .
Arlinghaus, C. S., Wulff, C., and Maier, G. W. (2024).“Revolutionizing Qualitative Human-Robot Interaction Research by Using GPT Models for Inductive Category Development”. Presented at the The 33rd IEEE International Conference on Robot and Human Interactive Communication (IEEE RO-MAN 2024), Pasadena.
Arlinghaus, C.S., Wulff, C., & Maier, G.W., 2024. Revolutionizing Qualitative Human-Robot Interaction Research by Using GPT Models for Inductive Category Development. Presented at the The 33rd IEEE International Conference on Robot and Human Interactive Communication (IEEE RO-MAN 2024), Pasadena.
C.S. Arlinghaus, C. Wulff, and G.W. Maier, “Revolutionizing Qualitative Human-Robot Interaction Research by Using GPT Models for Inductive Category Development”, Presented at the The 33rd IEEE International Conference on Robot and Human Interactive Communication (IEEE RO-MAN 2024), Pasadena, 2024.
Arlinghaus, C.S., Wulff, C., Maier, G.W.: Revolutionizing Qualitative Human-Robot Interaction Research by Using GPT Models for Inductive Category Development. Presented at the The 33rd IEEE International Conference on Robot and Human Interactive Communication (IEEE RO-MAN 2024), Pasadena (2024).
Arlinghaus, Clarissa Sabrina, Wulff, Charlotte, and Maier, Günter W. “Revolutionizing Qualitative Human-Robot Interaction Research by Using GPT Models for Inductive Category Development”. Presented at the The 33rd IEEE International Conference on Robot and Human Interactive Communication (IEEE RO-MAN 2024), Pasadena, 2024.
Link(s) zu Volltext(en)
Access Level
Closed Access
Google Scholar