67471 research outputs found
Sort by
Calibrating Trust in AI for Clinical Dentistry: A Qualitative Study of Human- AI Collaboration and Adoption Dynamics
Get PDFArtificial intelligence (AI) is increasingly integrated into clinical dentistry, offering enhancements in diagnostic accuracy, workflow efficiency, and decision-making support. However, its adoption remains uneven, largely due to challenges in trust calibration. This involves finding the right balance between overreliance and underuse. This qualitative study investigates how dental professionals perceive, develop, and recalibrate trust in AI tools, drawing on seven in-depth interviews with clinicians across specialties and geographies. Findings reveal three distinct user clusters: Cautious Verifiers, Balanced Validators, and Overreliant New Graduates, each with unique trust behaviors and verification strategies. Key factors influencing trust include interpretability, reliability, workflow integration, and clinician education. The study introduces an empirically grounded adaptation of the Inverted U-Model of AI Utilization, which links optimal performance to moderate verification (20–50% of AI outputs). These insights inform a trust-centered framework for safe and effective AI adoption, with implications for system design, training, and regulatory policy in dentistry and beyond
Law Meets GenAI: Using Artificial Intelligence to Derive Conceptual Models from Legal Regulations
Get PDFArtificial intelligence (AI) and conceptual models are both important to public organizations. AI and generative AI (GenAI) can help to cope with an increasing resource shortage, workload, and requirements, while conceptual models are essential for the design of IT systems. However, the combination of both, the creation of conceptual models using GenAI tools in public organizations, has been barely addressed in extant research. Thus, we investigate (1) how legal experts use GenAI tools when deriving conceptual models for public services from legal regulations and (2) what their experiences are in this use. In a qualitative study with 18 administrative legal experts we obtained various insights. For instance, we show that the participants either submitted strict instructions or conducted open conversations and they followed a top-down, bottom-up or combined approach in their analysis. The GenAI tools performed better in generating text-based models (forms) than graphic-based models (process models, decision trees)
On the Dark Side of AI Companions – How a Parasocial Preference for a Social Chatbot Can Lead to Pathological Chatbot Use
Get PDFSocial chatbots are becoming increasingly popular due to their ability to simulate human interactions and build socio-emotional relationships with users. However, along with the positive effects come potential risks. For example, a parasocial preference for a social chatbot could contribute to excessive and unregulated chatbot use, jeopardizing users' well-being. As the potential harms associated with social chatbots are largely unexplored, there is a need to integrate theories into the IS literature that explain the negative effects of a parasocial preference for a social chatbot. Therefore, we apply the cognitive- behavioral model of pathological internet use to human-chatbot interactions. We conducted two empirical studies and found that a parasocial preference contributes to deficient self-regulation regarding chatbot use and promotes the use of the chatbot for mood regulation. Furthermore, deficient self-regulation increases the risk of pathological chatbot use, especially among lonely users
Understanding How Professionals Integrate Generative AI into Team Meetings: A Qualitative Study
Get PDFTeam meetings are essential for coordination, knowledge exchange, and decision-making in organizations. As Generative AI (GenAI) becomes increasingly embedded in collaborative work, its role in shaping team dynamics remains underexplored. This study examines how professionals experience the integration of GenAI in team meetings and how it affects collaboration. We conducted five focus groups with 20 experienced users to explore GenAI’s impact in real contexts. Our analysis shows that GenAI does not merely automate routine work but actively influences participation patterns, negotiation of cognitive demands, and the redefinition of role boundaries. Distinctive mechanisms include altered entry pathways for junior employees and the reshaping of information flows within meetings—insights that extend beyond assumptions of efficiency gains. While participants reported benefits such as reduced administrative burden and faster onboarding, they also highlighted challenges in transparency and interaction. The study enriches collaboration research and offers practical guidance for integrating GenAI into meeting routines
Introduction to the Minitrack on Future of STEM Education and Workforce Development: Broadening Participation
No full textGoverning Generative AI Use through FAIR User Experience: Designing for Interactional Integrity
Get PDFPrevailing HCI paradigms in GenAI design prioritize harm prevention and abstract principles, such as transparency, but often neglect the embodied and interactive ways in which AI shapes user behavior and identity. This paper advocates for a fundamental shift, positioning “interactional integrity” as the central design goal and moving beyond a reductionist focus on harm minimization. We use the FAIR framework—grounded in the existential principles of Freedom, Authenticity, Intentionality, and Responsibility—to cultivate interactional integrity through interface-level affordances. By embedding these principles into user experience, the FAIR framework offers a systematic approach for integrating responsible AI into design practice, ensuring that responsible use becomes a lived interaction rather than a regulatory afterthought
Millionaire Shoppers’ Struggles? Exploring User Experiences with Ultra-Low-Cost E-Commerce Platforms through Text Mining
Get PDFThis study empirically analyzes consumer sentiment and behavior from user-generated reviews of ultra-low-cost e-commerce platforms, Temu and AliExpress. Using a Gated Recurrent Unit (GRU) model, reviews were classified as either positive or negative, while Latent Dirichlet Allocation (LDA) was employed to extract key thematic structures. A multiple regression analysis examined the influence of topics on review ratings, identifying structural links between emotions and evaluations. Results show that “delivery speed and convenience”, “value-for-money”, and “shopping convenience” drove positive sentiment. Conversely, “excessive marketing”, “system instability”, and “perceived quality issues” led to negative evaluations. Notably, the emergence of “ggang culture”—impulsive bulk buying followed by disposal—highlights a shift toward emotionally driven, irrational consumption behavior. This study contributes to quantifying the sentiment-topic-rating relationship, offering valuable implications for Chinese ultra-low-cost e-commerce expansion
Guided by the Bot, Driven by the Worker: Task Crafting and Emerging Competencies in GenAI-Augmented Manufacturing
Get PDFAs AI reshapes manufacturing, understanding how workers adapt and develop new competencies is critical. This study offers a grounded, step-by-step model of task crafting in a digitally evolving manufacturing company, highlighting how employees respond to misalignments by redesigning tasks, tools and routines. Based on interviews and observations, the findings reveal a recursive process driven by experiential knowledge, collaboration, and local innovation. Generative AI chatbots (e.g., ChatGPT) augment this process by supporting ideation, automation and informal learning, without displacing human agency. Generative AI supports micro-reskilling and hybrid competencies as a digital companion. This study contributes to job crafting literature by framing competence development as emergent and situated, and to Generative AI-in-manufacturing debates by showing how human-AI collaboration unfolds in practice. It offers implications for workforce transformation strategies aligned with Industry 5.0, where AI and human expertise co-evolve in dynamic, socially embedded ways
Analyzing Information-Seeking Behaviors in a Hakka AI Chatbot: A Cognitive-Pragmatic Study
Get PDFWith many endangered languages at risk of disappearing, efforts to preserve them now rely more than ever on using technology alongside culturally informed teaching strategies. This study examines user behaviors in TALKA, a generative AI-powered chatbot designed for Hakka language engagement, by employing a dual-layered analytical framework grounded in Bloom’s Taxonomy of cognitive processes and dialogue act categorization. We analyzed 7,077 user utterances, each carefully annotated according to six cognitive levels and eleven dialogue act types. These included a variety of functions, such as asking for information, requesting translations, making cultural inquiries, and using language creatively. Pragmatic classifications further highlight how different types of dialogue acts—such as feedback, control commands, and social greetings—align with specific cognitive intentions. The results suggest that generative AI chatbots can support language learning in meaningful ways—especially when they are designed with an understanding of how users think and communicate. They may also help learners express themselves more confidently and connect with their cultural identity. The TALKA case provides empirical insights into how AI-mediated dialogue facilitates cognitive development in low-resource language learners, as well as pragmatic negotiation and socio-cultural affiliation. By focusing on AI-assisted language learning, this study offers new insights into how technology can support language preservation and educational practice