Touch Your Heart: A Tone-aware Chatbot for Customer Care on Social Media

TL;DR

This paper introduces a novel tone-aware chatbot for social media customer care that enhances user experience by generating empathetic responses, trained on extensive real-world data, and performs comparably to human agents.

Contribution

The work presents a new deep learning chatbot that incorporates tone awareness, supported by formative research and trained on over 1.5 million real conversations.

Findings

Chatbot responses are as appropriate as human agents.

The chatbot is perceived as more empathetic than humans.

Significant influence of tone on user experience was uncovered.

Abstract

Chatbot has become an important solution to rapidly increasing customer care demands on social media in recent years. However, current work on chatbot for customer care ignores a key to impact user experience - tones. In this work, we create a novel tone-aware chatbot that generates toned responses to user requests on social media. We first conduct a formative research, in which the effects of tones are studied. Significant and various influences of different tones on user experience are uncovered in the study. With the knowledge of effects of tones, we design a deep learning based chatbot that takes tone information into account. We train our system on over 1.5 million real customer care conversations collected from Twitter. The evaluation reveals that our tone-aware chatbot generates as appropriate responses to user requests as human agents. More importantly, our chatbot is perceived to be even more empathetic than human agents.