A New Chatbot for Customer Service on Social Media
Top Cited Papers
- 2 May 2017
- conference paper
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 3506-3510
- https://doi.org/10.1145/3025453.3025496
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.Keywords
This publication has 11 references indexed in Scilit:
- Smart ReplyPublished by Association for Computing Machinery (ACM) ,2016
- EmpathPublished by Association for Computing Machinery (ACM) ,2016
- Towards crowd-based customer servicePublished by Association for Computing Machinery (ACM) ,2014
- Customer engagement in a Facebook brand communityManagement Research Review, 2012
- Facts or friends?Published by Association for Computing Machinery (ACM) ,2009
- Predictors of answer quality in online Q&A sitesPublished by Association for Computing Machinery (ACM) ,2008
- BLEUPublished by Association for Computational Linguistics (ACL) ,2001
- Service Quality: A Measure of Information Systems EffectivenessMIS Quarterly, 1995
- A Test of Services Marketing Theory: Consumer Information Acquisition ActivitiesJournal of Marketing, 1991
- Qualitative Analysis for Social ScientistsPublished by Cambridge University Press (CUP) ,1987