Logo des Repositoriums

Auflistung nach Autor:in "Gnewuch, Ulrich"

1 - 4 von 4
  • Konferenzbeitrag
    BotOrNot: A Platform for Conducting Experiments with Undisclosed Chat Agents
    (Mensch und Computer 2022 - Tagungsband, 2022) Hanschmann, Leon; Gnewuch, Ulrich; Maedche, Alexander
    Chatbots are omnipresent in today's online environments in work and private life. While early chatbots were easy to identify, recently released open-domain chatbots, such as GPT3 and Blenderbot2, increasingly blur the line between human and chatbot interaction. Dedicated research is required to better understand how different design configurations of open-domain chatbots impact their users, whether users are able to distinguish between human and bot chat agents, and how users respond to the undisclosed identity of their counterpart. However, there is a lack of experimental platforms that integrate state-of-the-art chatbots in order to enable such research. We therefore propose BotOrNot, which enables large-scale experimental research with participants in a Turing test setting. Participants are matched with either Blenderbot2/GPT3 or another human participant and tasked to figure out whether the counterpart is a human or bot. We designed the platform in a way that it allows to adapt the settings of the experiment to enable different experimental scenarios and follow an open approach allowing to integrate future bots via an API. Participants can personalize their avatars and chatbots can also be personalized with regards their personality and avatar.
  • Zeitschriftenartikel
    Interaktion mit smarten Systemen — Aktueller Stand und zukünftige Entwicklungen im Bereich der Nutzerassistenz
    (Wirtschaftsinformatik & Management: Vol. 9, No. 5, 2017) Morana, Stefan; Friemel, Celina; Gnewuch, Ulrich; Maedche, Alexander; Pfeiffer, Jella
  • Zeitschriftenartikel
    Multiexperience
    (Business & Information Systems Engineering: Vol. 64, No. 6, 2022) Gnewuch, Ulrich; Ruoff, Marcel; Peukert, Christian; Maedche, Alexander
  • Zeitschriftenartikel
    Opposing Effects of Response Time in Human–Chatbot Interaction
    (Business & Information Systems Engineering: Vol. 64, No. 6, 2022) Gnewuch, Ulrich; Morana, Stefan; Adam, Marc T. P.; Maedche, Alexander
    Research has shown that employing social cues (e.g., name, human-like avatar) in chatbot design enhances users’ social presence perceptions and their chatbot usage intentions. However, the picture is less clear for the social cue of chatbot response time. While some researchers argue that instant responses make chatbots appear unhuman-like, others suggest that delayed responses are perceived less positively. Drawing on social response theory and expectancy violations theory, this study investigates whether users’ prior experience with chatbots clarifies the inconsistencies in the literature. In a lab experiment ( N = 202), participants interacted with a chatbot that responded either instantly or with a delay. The results reveal that a delayed response time has opposing effects on social presence and usage intentions and shed light on the differences between novice users and experienced users – that is, those who have not interacted with a chatbot before vs. those who have. This study contributes to information systems literature by identifying prior experience as a key moderating factor that shapes users’ social responses to chatbots and by reconciling inconsistencies in the literature regarding the role of chatbot response time. For practitioners, this study points out a drawback of the widely adopted “one-design-fits-all�? approach to chatbot design.