Understanding and Designing Social Cues for Chatbots

Despite being hyped as the future of customer service, adoption and use of chatbots is growing much slower than expected. Organizations have realized that chatbots are not only about implementing state-of-the-art natural language processing capabilities, but also about the social elements that are always involved when users interact with human-like technologies. To address the lack of knowledge on how to design these social cues for chatbots in customer service, this dissertation project aims to:

  1. Provide a comprehensive overview of the sheer number and different categories of social cues (e.g., visual or verbal cues) for chatbots and voice assistants
  2. Conduct lab, online, and field experiments to systematically analyze and evaluate how different design options of social cues shape users’ perceptions, adoption decisions, and use of chatbots
  3. Integrate findings from the experiments to provide prescriptive knowledge for designing effective social cues for chatbots following the design science research approach
    Related publications:

  • Gnewuch, U., Morana, S., Adam, M. T. P., and Maedche, A. 2018. “Faster Is Not Always Better: Understanding the Effect of Dynamic Response Delays in Human-Chatbot Interaction,” in Proceedings of the 26th European Conference on Information Systems (ECIS 2018), Portsmouth, United Kingdom. Download Publication
  • Gnewuch, U., Morana, S., and Maedche, A. 2017. “Towards Designing Cooperative and Social Conversational Agents for Customer Service,” in Proceedings of the 38th International Conference on Information Systems (ICIS 2017), Seoul, South Korea. Download Publication

Project categories: Projects

Go top