67471 research outputs found
Sort by
Investigating Engagement in Semi-Synchronous Online Collaboration
Full text linkKnowledge work is increasingly conducted in various temporary knowledge collaborations, where participant engagement is critical for successful outcomes. Collaboration modes can vary from synchronous to asynchronous. To investigate knowledge worker engagement on a digital collaboration platform, we conducted a systematic literature review to identify key themes of engagement in semi-synchronous knowledge collaboration. Given the limited previous research on this topic, this study uses a multi-method approach to increase understanding of this timely topic. We interviewed knowledge workers to explore factors supporting or hindering their engagement. The results give insight into the opportunities and challenges of semi-synchronous knowledge collaboration on digital platforms. The paper contributes to research and practice on participant engagement in knowledge collaboration on digital platforms
Deep Learning vs. Novice User for Needle Tip Tracking in Ultrasound-Guided Intravenous Access
Full text linkBackground:. Ultrasound guided peripheral intravenous (US-pIV) access can reduce patient morbidity and mortality and improve the quality of care. Currently, there are no out-of-plane artificial intelligence tools designed to help learners reach competency with this procedure. Methods: We developed a deep learning (DL) model to identify needle-tip tracking during simulated US-pIV placement with out-of-plane technique. The sensitivity and specificity of this DL model was compared to a novice participant group. Results: Our DL model outperformed our novice group with an increased accuracy score (0.89 vs. 0.82 (95% CI 0.79–0.85), and higher sensitivity (0.91 vs. 0.82 (95% CI 0.79–0.85) and specificity scores (0.85 vs. 0.81 (95% CI 0.74–0.86), although these differences were not statistically significant. Conclusion: DL has the potential to enhance the learning curve associated with performing US-pIV access to ensure safer and more efficient outcomes for patients
Structure Preserving Dynamic Graphs for Power Systems
No full textLarge-scale integration of renewable energy resources presents the challenge of coordinating the output of numerous small generators and loads. This coordination problem typically involves solving a large centralized optimization problem. The growing number of decision variables associated with renewable resources increases the computational complexity of this coordination problem. Several approaches address this issue by decomposing the centralized problem into smaller, more computationally tractable subproblems. In this work, we extend the Kron-reduced dynamic graph to a structure-preserving model using the framework of non-uniform Kuramoto oscillators. We demonstrate how slow coherency can be used to identify groups of dynamically coherent nodes on the IEEE 14-bus test system, which can then serve as a basis for decomposing the centralized coordination problem
Creativity in Human-AI Co-Creation: A Two-Stage Model and the Da Vinci Score
Full text linkStandard collaborative systems for creative problem-solving and innovation often focus on process efficiency rather than the content of ideas. Generative artificial intelligence (GenAI) promises a shift: it can actively generate and evaluate ideas, potentially transforming innovation workflows. Integrating concepts from group support systems and collaboration engineering, we propose a two-stage model of human–AI co-creation. In Stage 1 (AI-seeded ideation), the AI rapidly establishes a foundation by generating knowable ideas; in Stage 2 (human-enhanced ideation), humans engage in unpatterned ideation using this AI-generated output, both refining initial ideas and introducing content gains/losses that extend traditional process gains/losses frameworks. We further define the Da Vinci Score as a composite creativity metric that enables differential weighting of criteria, aligning evaluation with business relevance and practical collaboration. Our three-condition hypotheses (AI-only, Human-only, Hybrid), partially supported by prior data, highlight implications for innovation practice, process design, and future research in business contexts
Navigating the Paradox: The Dynamic AI Trust Framework for Ethical Persuasion in Digital Marketing
Full text linkGenerative Artificial Intelligence (GenAI) is reshaping digital marketing by enabling more personalized content and persuasive user experiences at scale. While these capabilities offer significant value to marketers, they also heighten consumer concerns about data privacy, algorithmic transparency, and the authenticity of AI-generated content. This paper introduces the Dynamic AI Trust Framework, a conceptual model that explores how GenAI’s persuasive functions interact with consumer trust and privacy perceptions in digital environments. The framework outlines five interrelated dimensions — algorithmic transparency, user control and agency, data sourcing and security, fairness and bias mitigation, and authenticity and disclosure — as critical components for designing trustworthy and ethical AI-driven marketing strategies. By clarifying how these dimensions operate in practice, the framework provides a foundation for balancing innovation with responsibility, helping brands engage consumers more effectively while respecting their evolving expectations around data and trust
Introduction to the Minitrack on Practitioner Research Insights: Applications of Science and Technology to Real-World Innovations
No full textThe Path to Comprehensiveness: An LLM-Enhanced Systematic Literature Review on the Innovation Mindset
Full text linkThe study of the innovation mindset is not a new endeavor within and outside business and management. However, most of the studies and meta-analyses that have been undertaken on the topic rely on manual coding or simple keyword filters, thereby possibly missing some key artifacts due to the sheer scope of the daunting task. In this work, we try to overcome the comprehensiveness problem by introducing a multi‑LLM ensemble pipeline that integrates DeepSeekR1, Llama3, and QWEN models to retrieve, classify, and thematically cluster scholarly articles. Applying the pipeline to 106 peer‑reviewed publications, we identify four recurrent themes: (A) Creativity‑Risk Synergy, (B) Innovation Capacity, (C) Entrepreneurial Orientation, and (D) Adaptability and Problem Solving. These combinations improve over author‑supplied keywords, demonstrating the methodological value of using LLM models. The identified themes clarify the key needs for further research into the innovation mindset and offer an agenda for future explorations in information systems sciences
