Most chatbots and other types of digital assistants are given a name, are represented by a human-looking avatar, or are endowed with a personality. As a result, users often treat them like human beings and build social relationships with them. To better understand why and how these phenomena occur, this project investigates different designs of social cues and their effect on user perception and behavior. [Read more]
Today, many chatbots are implemented as human-AI hybrids that combine automation with a “human in the loop” approach. However, most hybrid chatbots do not disclose their true hybrid identity to customers or when the conversation is taken over by a human agent. This project aims to shed light on how self-disclosure affects customers and provider outcomes. [Read more]
There is limited design knowledge and tool support that guides chatbot engineers to design social chatbots. To address this challenge, we follow a design science research approach and investigates design principles that should guide the effective and efficient development of social chatbots. [Read more]
The assessment of psychological symptoms (e.g., depression, anxiety, stress) using screening questionnaires can be done via several modalities. While chatbots are seen as a promising alternative to traditional modalities, it is unclear how patients’ responses to chatbots would differ from other well-established modalities. Therefore, this project investigates how survey chatbots affect social desirability response bias in the context of mental health screenings. [Read more]
In the last years affective technologies have become more advanced and innovative. They allow for detailed and better understanding of human emotions by machines.These advances in affective computing have given rise to new abilities for chatbots to evolve from machine-like entities into partners for humans. With emotional cabapilites, such systems serve as potential emotional managers within team collaboration. [Read more]
In recent years, many public and private organizations are starting discussions about the moral and ethical perspective on technological advancements of artificial intelligence (AI). We investigate the design and effect of anthropomorphic capabilities of both, text- and speech-based chatbots, especially, social cues and the emotional capabilities of Affective Chatbots. We take this call to action and investigate how to design chatbots so that they support the users but do not harm anyone. At the same time they should create benefits for the community. [Read more]
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 skill sets and expertise to engage in innovative research projects and to strengthen the exchange between research and practice. Our partnerships can take various forms, including project-based collaboration, research scholarships, and publicly funded projects.
The entire Chatbot Research team attended the virtual European Conference on Information Systems (ECIS 2020). We presented three papers: “The Effect of Perceived Similarity in Dominance on Customer Self-Disclosure to Chatbots in Conversational Commerce”, “Towards Design Principles for Trustworthy Affective Chatbots for Virtual Teams”, and “We see we disagree: Insights from Designing a Cooperative Requirements Prioritization System”.
The entire Chatbot Research team attended the International Conference on Information Systems (ICIS 2019) in Munich. We participated in several workshops and Jasper presented our paper on “Designing a Chatbot Social Cue Configuration System”.
Ulrich gave a presentation about our research on the design of chatbots at this year’s Chatbot Summit in Berlin. He shared insights on why chatbots are perceived as human(-like) and how this phenomenon affects user interaction and behavior.
Our research group participated at CONVERSATIONS 2019, the 3rd International Workshop On Chatbot Research in Amsterdam, Netherlands. Ulrich Gnewuch and Jasper Feine presented the accepted full paper “Gender Bias in Chatbot Design” and had a great exchange with fellow chatbot researchers from all around Europe.
Stefan presented selected research projects in an invited research talk at the University of St. Gallen. The research groups of Prof. Matthias Söllner and Prof. Dr. Jan Marco Leimeister invited us to share our insights on the design of the human-chatbot interaction.
Stefan presented selected research results of the research group at the 2019 SAP User Assistance Reloaded conference. In this talk, he specifically emphasized the importance human-chatbot interaction design.
Our research group participated at International Conference on Wirtschaftsinformatik (WI) 2019 in Siegen, Germany. We presented two papers: “Measuring Service Encounter Satisfaction with Customer Service Chatbots using Sentiment Analysis” and “The Impact of Anthropomorphic and Functional Chatbot Design Features in Enterprise Collaboration Systems on User Acceptance” and Prof. Mädche led a panel discussion on “AI-based Digital Assistants – Opportunities and Risks.
The Institute of Information Systems and Marketing (IISM) presented contemporary chatbot research at a dedicated booth at the SAP UX Day. The SAP UX Day is organized by SAP once a year and took place on February 19th 2019 at ZKM. The SAP UX Day is an SAP-internal event, selected parterns and customers are invited. The event attracted approx. 800 participants.
Our research group attended the International Conference on Information Systems (ICIS 2018) in San Francisco, USA. Ulrich presented our paper on “The Chatbot is typing… – The Role of Typing Indicators in Human-Chatbot Interaction” at the SIG-HCI Workshop and Stefan gave a talk on “AI-Enabled User Assistance: Designing Human-Intelligent System Cooperation”.
As part of a seminar on “Digital Customer Interaction” organized by ASEW, a network for public utility companies in Germany, Ulrich gave a presentation on opportunities and challenges of customer service chatbots for energy companies.
The User Experience Day took place on October 11th 2018 in Mannheim and attracted 450 participants. Prof. Maedche was co-organizer of the UX Day . Stefan presented our work in the field of chatbots.
Stefan and Ulrich attended the European Conference on Information Systems (ECIS 2018) in Portsmouth, UK and presented our paper on “Faster is Not Always Better: Understanding the Effect of Dynamic Response Delays in Human-Chatbot Interaction”.
Stefan and Ulrich attended the International Conference on Information Systems (ICIS 2017) in Seoul, South Korea and presented our paper on “Towards Designing Cooperative and Social Conversational Agents for Customer Service”.
Prof. Maedche was the keynote speaker at the BEMD Jahreskongress in Dortmund, Germany. In his keynote, he also presented our research on the design of chatbots to decision makers in the energy industry.
Professor and Head of Research Group
Karlsruhe Institute of Technology (KIT)
Institute of Information Systems and Marketing (IISM)
Research Group Information Systems and Service Design