The influence of emotions and communication style on customer satisfaction and recommendation in a call center context: An NLP-based analysis
Baecke, Philippe Goedertier, Frank
Baecke, Philippe
Goedertier, Frank
Citations
Altmetric:
Publication Type
Journal article with impact factor
Editor
Supervisor
Publication Year
2025
Journal
Journal of Business Research
Book
Publication Volume
189
Publication Issue
February
Publication Begin page
Publication End page
Publication Number of pages
Collections
Abstract
We study the impact of customer sentiment, agent sentiment, and emotional matching (i.e., call center agents matching emotional expressive states of customers) on satisfaction and recommendation intentions in a utilitarian service context. We methodologically contribute by text mining observed data using advanced transformer-based NLP algorithms and compare findings with those of previous survey-based research. An analysis of 25008 call center conversations reveals that positive (vs negative) customer sentiment more strongly impacts satisfaction and recommendation. For recommendation (vs satisfaction) we observe that negative emotional expressions have a relatively stronger weight, albeit less strong than that of positive ones. We find that emotional expressions of call center agents (vs those of clients) have a smaller impact on these outcomes. Emotional matching is observed as beneficial, but not necessarily when faced with negative high-arousal emotional expressions. As conceptual grounding, we refer to theorizing around delight, formality, source credibility, emotional arousal and loss aversion.
Research Projects
Organizational Units
Journal Issue
Keywords
Call Center, Emotion, Customer Satisfaction, Net promotor score (NPS), Computational Linguistics