Using Traditional Text Analysis and Large Language Models in Service Failure and Recovery
Conditionally Accepted at Journal of Service Research
17 Pages Posted: 14 Apr 2025
Date Written: December 16, 2024
Abstract
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 sub-field 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 (LLMs), 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.
Keywords: Service Failure and Recovery, Text Mining, NLP, Language Theory, Large Language Models (LLMs), Machine Learning
Suggested Citation: Suggested Citation