Loading...
Analyzing Patterns of Conversational Breakdown in Human-Chatbot Customer Service Conversations
Braggaar,Anouck Kunneman,Florian van Miltenburg,Emiel
Braggaar,Anouck
Kunneman,Florian
van Miltenburg,Emiel
Abstract
Many chatbots still struggle with correctly interpreting and responding to user enquiries. Therefore, it is important to figure out how and why chatbot-human conversations break down. In this study we analyzed features in user-utterances directly before a bot-initiated repair to determine their presence and prominence as possible predictors of conversational breakdowns. For this study we used data from a real-life public transport customer service chatbot, showing the errors that occur in actual deployed systems. The analysis shows that there are some features (such as commonness, outdated words, and unexpected words) that occur more often in utterances directly before a repair. Some features also correlate with each other and occur together, such as outdated words and subjectivity. By using feature analysis, many opportunities for improvement can be found either live (during the interaction) or afterwards
Description
Date
2025-04-04
Journal Title
Journal ISSN
Volume Title
Publisher
Files
Loading...
Braggaar.pdf
Adobe PDF, 380.51 KB
Research Projects
Organizational Units
Journal Issue
Keywords
chatbots, customer service, breakdowns, features analysis
Citation
Braggaar, A, Kunneman, F & van Miltenburg, E 2025, 'Analyzing Patterns of Conversational Breakdown in Human-Chatbot Customer Service Conversations', pp. 3-22. https://doi.org/10.1007/978-3-031-88045-2_1