A New Chatbot for Customer Service on Social Media

TLDR

Customers increasingly use social media for support, but most requests remain unanswered or delayed. The study develops an automated chatbot to generate responses to social media customer requests. The chatbot uses advanced deep learning, trained on about one million Twitter exchanges from 60+ brands. Evaluation shows the chatbot handles emotional requests with empathy comparable to humans and outperforms a retrieval‑based system per human and automatic metrics.

Abstract

Users are rapidly turning to social media to request and receive customer service; however, a majority of these requests were not addressed timely or even not addressed at all. To overcome the problem, we create a new conversational system to automatically generate responses for users requests on social media. Our system is integrated with state-of-the-art deep learning techniques and is trained by nearly 1M Twitter conversations between users and agents from over 60 brands. The evaluation reveals that over 40% of the requests are emotional, and the system is about as good as human agents in showing empathy to help users cope with emotional situations. Results also show our system outperforms information retrieval system based on both human judgments and an automatic evaluation metric.