We are passionate about studying the design, use, and impact of AI-powered chatbots and voice assistants in work and life.
Our research at the intersection of information systems (IS) and human-computer interaction (HCI) aims to provide both theoretical contributions and useful insights for developers, managers, and policymakers.
Projects
Many chatbots are designed to look and act like humans (e.g., by giving them names and avatars). Why is that? And how do these social cues influence our interaction with chatbots? In this project, we aim to answer these questions by providing a comprehensive overview of social cues and examining their impact on human-chatbot interaction.
It is difficult to completely avoid conversational breakdowns in customer–chatbot interaction, resulting in frustrated and dissatisfied customers. To address this problem, we design and evaluate more effective repair strategies (e.g., human employee involvement, more specific repair messages) and test their impact in the field with real customers.
Mental health issues, such as depression, are a large-scale problem with significant individual and socioeconomic costs. Yet, people often do not seek or receive treatment. Together with our colleagues from University of Greifswald, we design and evalute mental health chatbots and investigate how their personalization can contribute to treatment success.
Dashboards have become popular tools for visualizing, exploring, and analyzing data in business and society (e.g., COVID-19 dashboards). However, less tech-savvy users often struggle to find and extract the information they need. In our research, we address this problem by extending dashboards with a conversational user interface so that users can interact with a dashboard using natural language.
Chatbots often reach their limits in interactions with customers. However, since analyzing customer-chatbot interaction data is difficult and labor-intensive, existing limitations are not immediately apparent to both chatbot operators (e.g., customer service managers) and chatbot developers. Our research aims to address this challenge by developing novel chatbot analytics systems that can generate valuable insights for managers and developers.
Emotion-aware chatbots that can sense human emotions are becoming increasingly prevalent. In our research, we study how these chatbots can support team communication on collaboration platforms such as Slack and Microsoft Teams.
Developing chatbots is often more difficult and expensive than expected. In addition, domain experts and users are not (or only partially) involved in the development process. Our research tackles this challenge by developing interactive systems that support chatbot developers to build better chatbots.
With advances in robotics and AI, consumers will increasingly find themselves interacting with robot shopping assistants instead of human employees. Together with our partners at the Nuremberg Institute for Market Decisions (NIM), we leverage the social robot “Furhat” and large language models (LLMs) such as ChatGPT to design robot shopping assistants and investigate their impact on human decision-making in sales dialogs.
Selected Publications
(2023).
More than a Bot? The Impact of Disclosing Human Involvement on Customer Interactions with Hybrid Service Agents.
Information Systems Research (forthcoming).
(2023).
Designing Conversational Dashboards for Effective Use in Crisis Response.
Journal of the Association for Information Systems, 24(6), 1500–1526.
(2022).
Opposing Effects of Response Time in Human–Chatbot Interaction.
Business & Information Systems Engineering, 64, 773–791.
(2022).
Understanding the impact of control levels over emotion-aware chatbots.
Computers in Human Behavior, 129, 107122.
(2019).
A Taxonomy of Social Cues for Conversational Agents.
International Journal of Human-Computer Studies, 132, 138–161.
Recent Publications
(2023).
The New Dream Team? A Review of Human-AI Collaboration Research From a Human Teamwork Perspective.
Proceedings of the 44th International Conference on Information Systems (ICIS 2023).
(2023).
Saleshat: A LLM-based Social Robot for Human-Like Sales Conversations.
Proceedings of the 7th International Workshop on Chatbot Research (CONVERSATIONS 2023).
(2023).
Towards Designing a NLU Model Improvement System for Customer Service Chatbots.
Proceedings of the 18th International Conference on Wirtschaftsinformatik (WI 2023).
(2023).
Designing a Conversation Mining System for Customer Service Chatbots.
Proceedings of the 31st European Conference on Information Systems (ECIS 2023).
(2023).
Designing Amsl - A Digital Assistant for Self-Regulated Learning Overview.
Prooceedings of the 31st European Conference on Information Systems (ECIS 2023).
Our Partners
In our research, we collaborate with a strong network of national and international partners from academia and industry. We aim to bring together different people with different skills and expertise to engage in innovative research projects and strengthen the exchange between research and practice. Our partnerships can take various forms, including project-based collaboration, PhD scholarships, and publicly funded projects. If you would like to discuss collaboration opportunities, please get in touch with us: info@chatbotresearch.org.
Academic Partners
Industry Partners
People
Team Members @ KIT
Ulrich Gnewuch
Postdoc & Team Lead
Alexander Maedche
Professor
Daniel Schloß
PhD Student
Florian Onur Kuhlmeier
PhD Student
Leon Hanschmann
PhD Student
Till Carlo Schelhorn
PhD Student
Saskia Haug
PhD Student
Sven Scheu
PhD Student
Maximilian Kost
Research Assistant
Associated Researchers
Stefan Morana
Saarland University
Marcel Ruoff
Karlsruhe Institute of Technology
Fabian Reinkemeier
University of Göttingen
Stefan Lüttke
University of Greifswald
Alumni
Ivo Benke
Jasper Feine
Tim Rietz
Melanie Schulz
Contact
- info@chatbotresearch.org
- Karlsruhe Institute of Technology (KIT), Human-Centered Systems Lab, Kaiserstraße 89-93, 76133 Karlsruhe, Germany