Customer service is a setting that calls for empathy in live human agent responses. Recent advances have demonstrated how open-domain chatbots can be trained to demonstrate empathy when responding to live human utterances. We show that a blended skills chatbot model that responds to customer queries is more likely to resemble actual human agent response if it is trained to recognize emotion and exhibit appropriate empathy, than a model without such training. For our analysis, we leverage a Twitter customer service dataset containing several million customer<->agent dialog examples in customer service contexts from 20 well-known brands.
@article{arxiv.2101.01334,
title = {Evaluating Empathetic Chatbots in Customer Service Settings},
author = {Akshay Agarwal and Shashank Maiya and Sonu Aggarwal},
journal= {arXiv preprint arXiv:2101.01334},
year = {2021}
}