Tianran Hu
Jiebo Luo
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.
- Jennifer L Aaker. 1997. Dimensions of brand personality. Journal of marketing research (1997), 347--356.Google Scholar
- Masroor Ahmed. 2017. Social Media Customer Service Statistics and Trends. http://www.socialmediatoday.com/social-business/. (2017).Google Scholar
- Joan-Isaac Biel, Oya Aran, and Daniel Gatica-Perez. 2011. You Are Known by How You Vlog: Personality Impressions and Nonverbal Behavior in YouTube.. In ICWSM.Google Scholar
- Jeffrey G Blodgett, Donna J Hill, and Stephen S Tax. 1997. The effects of distributive, procedural, and interactional justice on postcomplaint behavior. Journal of retailing 73, 2 (1997), 185--210.Google ScholarCross Ref
- Christo Boshoff. 1997. An experimental study of service recovery options. International Journal of service industry management 8, 2 (1997), 110--130.Google ScholarCross Ref
- Scott Brave, Clifford Nass, and Kevin Hutchinson. 2005. Computers that care: investigating the effects of orientation of emotion exhibited by an embodied computer agent. International journal of human-computer studies 62, 2 (2005), 161--178. Google ScholarDigital Library
- Heloisa Candello, Claudio Pinhanez, and Flavio Figueiredo. 2017. Typefaces and the Perception of Humanness in Natural Language Chatbots. In CHI'17. ACM, 3476--3487. Google ScholarDigital Library
- Ting-Hao Kenneth Huang Joseph Chee Chang and Saiganesh Swaminathan Jeffrey P Bigham. 2017. Evorus: A Crowd-powered Conversational Assistant That Automates Itself Over Time. In UIST Poster 2017. Google ScholarDigital Library
- Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014).Google ScholarDigital Library
- Gary L Clark, Peter F Kaminski, and David R Rink. 1992. Consumer complaints: Advice on how companies should respond based on an empirical study. Journal of Consumer Marketing 9, 3 (1992), 5--14.Google ScholarCross Ref
- Moshe Davidow. 2000. The bottom line impact of organizational responses to customer complaints. Journal of hospitality & tourism research 24, 4 (2000), 473--490.Google ScholarCross Ref
- Moshe Davidow. 2003. Organizational responses to customer complaints: What works and what doesn't. Journal of service research 5, 3 (2003), 225--250.Google ScholarCross Ref
- Moshe Davidow and James Leigh. 1998. The effects of organizational complaint responses on consumer satisfaction, word of mouth activity and repurchase intentions. Journal of Consumer Satisfaction, Dissatisfaction and Complaining Behavior 11 (1998).Google Scholar
- Hyo Jin Do and Wai-Tat Fu. 2016. Empathic Virual Assistant for Healthcare Information with Positive Emotional Experience. In Healthcare Informatics (ICHI), 2016 IEEE International Conference on. IEEE, 318--318.Google ScholarCross Ref
- Sabine A Einwiller and Sarah Steilen. 2015. Handling complaints on social network sites--An analysis of complaints and complaint responses on Facebook and Twitter pages of large US companies. Public Relations Review 41, 2 (2015), 195--204.Google ScholarCross Ref
- Hans Jurgen Eysenck. 1953. The structure of human personality. (1953).Google Scholar
- Facebook. 2017. Facebook Conversation Agent System. https://www.facebook.com/ConversationAgent/. (2017).Google Scholar
- David Ha, Andrew Dai, and Quoc V Le. 2016. HyperNetworks. arXiv preprint arXiv:1609.09106 (2016).Google Scholar
- F Maxwell Harper, Daphne Raban, Sheizaf Rafaeli, and Joseph A Konstan. 2008. Predictors of answer quality in online Q&A sites. In CHI'08. ACM, 865--874. Google ScholarDigital Library
- Takayuki Hasegawa, Nobuhiro Kaji, Naoki Yoshinaga, and Masashi Toyoda. 2013. Predicting and Eliciting Addressee's Emotion in Online Dialogue.. In ACL (1). 964--972.Google Scholar
- Jonathan Herzig, Guy Feigenblat, Michal Shmueli-Scheuer, David Konopnicki, Anat Rafaeli, Daniel Altman, and David Spivak. 2016. Classifying Emotions in Customer Support Dialogues in Social Media.. In SIGDIAL Conference. 64--73.Google ScholarCross Ref
- Ting-Hao Kenneth Huang, Walter S Lasecki, Amos Azaria, and Jeffrey P Bigham. 2016. " Is There Anything Else I Can Help You With?" Challenges in Deploying an On-Demand Crowd-Powered Conversational Agent. In HCOMP'16.Google Scholar
- IBM. 2017. IBM Watson Automatic Chatbot Service. https://www.ibm.com/watson/services/conversation-2/. (2017).Google Scholar
- Doga Istanbulluoglu. 2017. Complaint handling on social media: The impact of multiple response times on consumer satisfaction. Computers in Human Behavior 74 (2017), 72--82.Google ScholarCross Ref
- L Kang, C Tan, and J Zhao. 2013. The impact of intra-transaction communication on customer purchase behaviour in e-commerce context. In ACIS'13. RMIT University, 1--12.Google Scholar
- Suin Kim, JinYeong Bak, and Alice Haeyun Oh. 2012. Do You Feel What I Feel? Social Aspects of Emotions in Twitter Conversations.. In ICWSM.Google Scholar
- Diederik Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).Google Scholar
- Michel Laroche, Mohammad Reza Habibi, and Marie-Odile Richard. 2013. To be or not to be in social media: How brand loyalty is affected by social media? International Journal of Information Management 33, 1 (2013), 76--82.Google ScholarCross Ref
- Walter S Lasecki, Rachel Wesley, Jeffrey Nichols, Anand Kulkarni, James F Allen, and Jeffrey P Bigham. 2013. Chorus: a crowd-powered conversational assistant. In Proceedings of the 26th annual ACM symposium on User interface software and technology. ACM, 151--162. Google ScholarDigital Library
- Jiwei Li, Michel Galley, Chris Brockett, Georgios P Spithourakis, Jianfeng Gao, and Bill Dolan. 2016. A persona-based neural conversation model. arXiv preprint arXiv:1603.06155 (2016).Google Scholar
- Jiwei Li, Will Monroe, Alan Ritter, Michel Galley, Jianfeng Gao, and Dan Jurafsky. 2016. Deep reinforcement learning for dialogue generation. arXiv preprint arXiv:1606.01541 (2016).Google Scholar
- Shoushan Li, Lei Huang, Rong Wang, and Guodong Zhou. 2015. Sentence-level Emotion Classification with Label and Context Dependence.. In ACL (1). 1045--1053.Google Scholar
- Jade Longelin. 2016. Customer Service Response and Waiting Time on Social Media. http://blog.playvox.com/ customer-service-response-and-waiting-time-on-social-media. (2016).Google Scholar
- Rhonda Mack, Rene Mueller, John Crotts, and Amanda Broderick. 2000. Perceptions, corrections and defections: implications for service recovery in the restaurant industry. Managing Service Quality: An International Journal 10, 6 (2000), 339--346.Google ScholarCross Ref
- François Mairesse and Marilyn Walker. 2007. PERSONAGE: Personality generation for dialogue. In Annual Meeting-Association For Computational Linguistics, Vol. 45. 496.Google Scholar
- Jennifer Langston Martin. 1985. Consumer perception of and response to corporate complaint handling... Ph.D. Dissertation. Texas Woman's University.Google Scholar
- Michael A McCollough. 2000. The effect of perceived justice and attributions regarding service failure and recovery on post-recovery customer satisfaction and service quality attitudes. Journal of Hospitality & Tourism Research 24, 4 (2000), 423--447.Google ScholarCross Ref
- Microsoft. 2017. Build a great conversationalist. https://dev.botframework.com/. (2017).Google Scholar
- Amy Mitchell and Dana Page. 2015. State of the news media 2015. Pew Research Center 29 (2015).Google Scholar
- Susan V Morris. 1988. How many lost customers have you won back today? An aggressive approach to complaint handling in the hotel industry. Journal of Consumer Satisfaction, Dissatisfaction and Complaining Behavior 1, 1 (1988), 86--92.Google Scholar
- Prashanth U Nyer. 2000. An investigation into whether complaining can cause increased consumer satisfaction. Journal of consumer marketing 17, 1 (2000), 9--19.Google ScholarCross Ref
- Shereen Oraby, Pritam Gundecha, Jalal Mahmud, Mansurul Bhuiyan, and Rama Akkiraju. 2017. How May I Help You?: Modeling Twitter Customer ServiceConversations Using Fine-Grained Dialogue Acts. In Proceedings of the 22nd International Conference on Intelligent User Interfaces. ACM, 343--355. Google ScholarDigital Library
- James W Pennebaker, Martha E Francis, and Roger J Booth. 2001. Linguistic inquiry and word count: LIWC 2001. Mahway: Lawrence Erlbaum Associates 71, 2001 (2001), 2001.Google Scholar
- Rosalind W Picard and Roalind Picard. 1997. Affective computing. Vol. 252. MIT press Cambridge. Google ScholarDigital Library
- Helmut Prendinger and Mitsuru Ishizuka. 2005. The empathic companion: A character-based interface that addresses users'affective states. Applied Artificial Intelligence 19, 3--4 (2005), 267--285.Google ScholarCross Ref
- Alan Ritter, Colin Cherry, and William B Dolan. 2011. Data-driven response generation in social media. In Proceedings of the conference on empirical methods in natural language processing. Association for Computational Linguistics, 583--593. Google ScholarDigital Library
- Beverley A Sparks and Janet R McColl-Kennedy. 2001. Justice strategy options for increased customer satisfaction in a services recovery setting. Journal of Business Research 54, 3 (2001), 209--218.Google ScholarCross Ref
- Martin Sundermeyer, Ralf Schlüter, and Hermann Ney. 2012. LSTM neural networks for language modeling. In Thirteenth Annual Conference of the International Speech Communication Association.Google ScholarCross Ref
- Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learning with neural networks. In Advances in neural information processing systems. 3104--3112. Google ScholarDigital Library
- TARP TARP. 1982. Measuring the grapevine consumer response and word-of-mouth. The Coca-Cola Company (1982).Google Scholar
- Anbang Xu, Zhe Liu, Yufan Guo, Vibha Sinha, and Rama Akkiraju. 2017. A New Chatbot for Customer Service on Social Media. In CHI'17. ACM, 3506--3510. Google ScholarDigital Library
- Peifeng Yin, Zhe Liu, Anbang Xu, and Taiga Nakamura. 2017. Tone Analyzer for Online Customer Service: An Unsupervised Model with Interfered Training. In Proceedings of the 26th ACM International on Conference on Information and Knowledge Management. 1887--1895. Google ScholarDigital Library
- Zhou Yu, Alexandros Papangelis, and Alexander Rudnicky. 2015. TickTock: A non-goal-oriented multimodal dialog system with engagement awareness. In Proceedings of the AAAI Spring Symposium.Google Scholar
- Lu Zhang, Lee B Erickson, and Heidi C Webb. 2011. Effects of "emotional text" on Online Customer Service Chat. (2011).Google Scholar
- Hao Zhou, Minlie Huang, Tianyang Zhang, Xiaoyan Zhu, and Bing Liu. 2017. Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory. arXiv preprint arXiv:1704.01074 (2017).Google Scholar
Index Terms
- Touch Your Heart: A Tone-aware Chatbot for Customer Care on Social Media
Recommendations
"I Hear You, I Feel You": Encouraging Deep Self-disclosure through a Chatbot
CHI '20: Proceedings of the 2020 CHI Conference on Human Factors in Computing SystemsChatbots have great potential to serve as a low-cost, effective tool to support people's self-disclosure. Prior work has shown that reciprocity occurs in human-machine dialog; however, whether reciprocity can be leveraged to promote and sustain deep self-...
Evaluating and Informing the Design of Chatbots
DIS '18: Proceedings of the 2018 Designing Interactive Systems ConferenceText messaging-based conversational agents (CAs), popularly called chatbots, received significant attention in the last two years. However, chatbots are still in their nascent stage: They have a low penetration rate as 84% of the Internet users have not ...
Chatbot with Touch and Graphics: An Interaction of Users for Emotional Expression and Turn-taking
CUI '20: Proceedings of the 2nd Conference on Conversational User InterfacesUse of chatbots for emotional exchange is recently increasing in various domains. However, as existing chatbots have been considered in terms of natural language processing techniques for interaction with text-based chatting, chatbot interaction with ...
Comments