Detecting user frustration in modern-day task-oriented dialog (TOD) systems is imperative for maintaining overall user satisfaction, engagement, and retention. However, most recent research is focused on sentiment and emotion detection in academic settings, thus failing to fully encapsulate implications of real-world user data. To mitigate this gap, in this work, we focus on user frustration in a deployed TOD system, assessing the feasibility of out-of-the-box solutions for user frustration detection. Specifically, we compare the performance of our deployed keyword-based approach, open-source approaches to sentiment analysis, dialog breakdown detection methods, and emerging in-context learning LLM-based detection. Our analysis highlights the limitations of open-source methods for real-world frustration detection, while demonstrating the superior performance of the LLM-based approach, achieving a 16% relative improvement in F1 score on an internal benchmark. Finally, we analyze advantages and limitations of our methods and provide an insight into user frustration detection task for industry practitioners.

Task-Oriented Dialog (TOD) systems often suffer from dialog breakdowns - situations in which users cannot or do not want to proceed with the conversation. Ideally TOD systems should be able to detect dialog breakdowns to prevent users from quitting a conversation and to encourage them to interact with the system again. In this paper, we present BETOLD, a privacy-preserving dataset for breakdown detection. The dataset consists of user and system turns represented by intents and entity annotations, derived from NLU and NLG dialog manager components. We also propose an attention-based model that detects potential breakdowns using these annotations, instead of the utterances’ text. This approach achieves a comparable performance to the corresponding utterance-only model, while ensuring data privacy.