Using Traditional Text Analysis and Large Language Models in Service Failure and Recovery
Journal of Service Research · 2025-08 · 28 (3) · 382-388
DOI: 10.1177/10946705241307678 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Service Research, online erschienen am 04.02.2025. Verfasst von Francisco Villarroel Ordenes und 3 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 8 Literaturangaben.
Abstract (Originalsprache)
Service failure and recovery (SFR) typically involves one or more people (or machines) talking or writing to each other in a goal-directed conversation. While SFR represents a prime context to understand how language reflects and shapes the service experience, this subfield has only begun to apply text analysis methods and language theories to this context. This tutorial offers a methodological guide for traditional text analysis methods and large language models and suggests some future research paths in SFR. We also provide user-friendly workflow repositories, in Python and KNIME Analytics, that researchers with (and without) coding experience can use. In doing so, we hope to encourage the next wave of text analysis in SFR research.
Zitieren
APA
Ordenes, F. V., Packard, G., Hartmann, J., & Proserpio, D. (2025). Using Traditional Text Analysis and Large Language Models in Service Failure and Recovery. Journal of Service Research, 28(3), 382-388. https://doi.org/10.1177/10946705241307678
Vancouver
Ordenes FV, Packard G, Hartmann J, Proserpio D. Using Traditional Text Analysis and Large Language Models in Service Failure and Recovery. Journal of Service Research. 2025;28(3):382-388. doi:10.1177/10946705241307678
BibTeX
@article{Ordenes2025,
author = {Ordenes, Francisco Villarroel and Packard, Grant and Hartmann, Jochen and Proserpio, Davide},
title = {Using Traditional Text Analysis and Large Language Models in Service Failure and Recovery},
journal = {Journal of Service Research},
year = {2025},
volume = {28},
number = {3},
pages = {382--388},
doi = {10.1177/10946705241307678}
}
EUVIMED