Logo des Repositoriums

Auflistung nach Schlagwort "human-AI interaction"

1 - 5 von 5
  • Workshopbeitrag
    Autocompletion as a Basic Interaction Concept for User-Centered AI
    (Mensch und Computer 2020 - Workshopband, 2020) Lehmann, Florian; Buschek, Daniel
    With this position paper we propose that autocompletion can be interpreted as a basic interaction concept in the interaction between humans and systems using artificial intelligence (AI). Autocompletion is well known from text input where the system predicts intended user input, e.g. in search engines. In our research on human-AI collaboration we observe parallels to such textual autocompletion but in different application contexts, such as text generation, mock-up generation, and layout solvers. We compare exemplary related work to highlight autocompletion as a reoccurring and reusable interaction concept. We discuss that identifying underlying interaction primitives in user-centered AI can help to inform concrete design solutions for interactions and user interfaces, and could be a starting point for future research in this area.
  • Konferenzbeitrag
    Comparative analysis of AI facilitator impact in online discussions: A cross-cultural study
    (INFORMATIK 2024, 2024) Sahab, Sofia; Haqbeen, Jawad A.; Ito, Takayuki
    AI chatbots are helpful in facilitating group discussions in online forums while enhancing users’ engagement and interaction. However, whether the AI chatbot as a facilitator influences users to express their opinions may depend on factors such as users' social presence, knowledge on discussion topics, and their desire to express their opinions. The effectiveness of social qualities of agents in collecting various opinions across different cultural contexts in online discussions needs further research. This paper investigates the effect of facilitation chatbots in collecting various opinions in two countries with distinct socio-cultural and economic backgrounds, Afghanistan and Japan. In an experimental study (n=32), we found that chatbots significantly impact discussion development with groups knowledgeable about the discussion topic (vs. less knowledgeable individuals). Additionally, self-disclosure, influenced by specific social contexts, encourages users to post their opinions more freely, affecting levels of social presence and opinion expression in chatbot-assisted online forums. Our findings provide a basis for designing tools that enhance idea development in online communities with distinct socio-cultural and economic backgrounds.
  • Konferenzbeitrag
    Configurations of human-AI work in agriculture
    (43. GIL-Jahrestagung, Resiliente Agri-Food-Systeme, 2023) Hüllmann, Joschka Andreas; Precht, Hauke; Wübbe, Carolin
    Agriculture is making leaps in digitalization and the development of artificial intelligence (AI) systems, e.g., decision support systems, sensors, or autonomous vehicles. However, adoption and widespread use of these technologies remains below expectations with negative consequences for digitally advancing the agricultural industry. Therefore, this study investigates the configurations of human-AI work, in particular, human-AI decision-making. Configurations describe the interactions between workers and intelligent systems, emphasizing the adoption and use of technologies in-situ. This study targets agricultural farms in Germany, collecting qualitative data at small and medium-sized businesses. From this data, the paper examines how configurations of human-AI work emerge and how explanations influence these configurations in the context of agricultural work. Theoretical contributions include a new understanding of how agricultural workers adopt and work with AI to make decisions. Practical contributions include more accessible AI systems, easing transfer into practice, and improving agricultural workers’ interactions with AI.
  • Zeitschriftenartikel
    Examining Autocompletion as a Basic Concept for Interaction with Generative AI
    (i-com: Vol. 19, No. 3, 2021) Lehmann, Florian; Buschek, Daniel
    Autocompletion is an approach that extends and continues partial user input. We propose to interpret autocompletion as a basic interaction concept in human-AI interaction. We first describe the concept of autocompletion and dissect its user interface and interaction elements, using the well-established textual autocompletion in search engines as an example. We then highlight how these elements reoccur in other application domains, such as code completion, GUI sketching, and layouting. This comparison and transfer highlights an inherent role of such intelligent systems to extend and complete user input, in particular useful for designing interactions with and for generative AI. We reflect on and discuss our conceptual analysis of autocompletion to provide inspiration and a conceptual lens on current challenges in designing for human-AI interaction.
  • Konferenzbeitrag
    Facilitation chatbots enhance student confidence in learning platforms
    (INFORMATIK 2024, 2024) Haqbeen, Jawad A.; Sahab, Sofia; Ito, Takayuki
    The recent development of Large Language Models (LLMs) in the last two years has enhanced the potential of creating facilitation chatbots that enhance creativity and productivity in the online community. However, the impact of facilitation chatbots on learning confidence is yet to be clearly articulated. In this study, we introduce facilitation agents that implement understanding and content-generation capabilities on learning platforms with the participation of undergraduate students. It explores the potential of LLMs to enrich pre- and post-lecture discussions by providing diverse viewpoints and stimulating engagement with lecture contents among participants. In this paper, we investigated the effect of facilitation chatbots on students' learning confidence during synchronous e-learning courses. In the control experimental study (n=80), we found that chatbots induced learning confidence most effectively, making students experience strong confidence in the learning platform, likely due to the chatbot's contextual knowledge and human touch. Our study provides insight into creating effective chatbots to enhance students' confidence, skills, benefits, and involvement in the pre- and post-learning processes.