Selecting empathic response headers in customer support conversations with LLM-based emotion recognition
Author(s)
Date Issued
2024
Publisher
Springer
Related Publication(s)
Chatbots and Human-centered AI (8th International Workshop of CONVERSATIONS 2024) Revised Selected Papers
Start page
23
End page
32
Abstract
This research considers the task of automatically adding empathic headers (e.g., “Sorry to hear that.”) to agent responses in customer support conversations. We employ a task-oriented dialogue (TOD) response selection model which allows response headers to be selected from existing corpora of conversations. Since the model is not fine-tuned with information about emotions in tweets, it is supplemented by filtering based on emotion annotations. The open-sourced LLM Llama 3.1 is employed for providing these annotations. We devise an experiment to evaluate this approach by automatic means. The preliminary results are discussed.
SFU Affiliated Publication
Yes
Availability at SFU Library
No database links found.