67471 research outputs found
Sort by
Embracing Uncertainty in Human Activity Recognition: A Fuzzy Logic Framework for Interpretable and Context-aware Reasoning
Full text linkHuman Activity Recognition (HAR) in real-world environments is inherently uncertain — shaped by ambiguous sensor signals, behavioral variability, and contextual dynamics that challenge traditional machine learning approaches. Despite growing interest in robustness and explainability, most current systems still treat uncertainty as a nuisance to be minimized rather than a structural feature to be modeled. This paper proposes a conceptual shift: positioning fuzzy logic as the core paradigm for designing HAR systems that are interpretable, adaptive, and uncertainty-aware. We present a theoretical framework in which fuzzy reasoning is integrated throughout the HAR pipeline— from sensor abstraction and context modeling to soft, interpretable activity inference and natural language explanations. By framing uncertainty as a representational and inferential asset, rather than a limitation, our approach enables systems that align more closely with the complexity of human behavior and the demands of human-centered AI. The framework is modular, extensible, and designed for transparency— making it suitable for long-term deployment in smart environments, particularly in domains like elderly care, remote monitoring, and assistive technologies. This work contributes a structured foundation for building next-generation HAR systems that move beyond black-box classification, supporting ethical, explainable, and context-sensitive activity recognition
Design for Function, not Feeling: How Data-Driven Product Design Influences Consumer Perception
Full text linkAs product-service systems become increasingly important, product design takes on a crucial role. Companies use Data-Driven Product Design (DDPD) to boost product development while simultaneously benefiting their services. However, research has not yet analyzed how consumers perceive products that are developed using DDPD. This quantitative study investigates how DDPD influences consumer perception and how this is moderated by consumers' purchase motivation. An online vignette experiment was conducted to measure consumer perception of a smartphone across seven product dimensions. Using structural equation modeling, results show that DDPD significantly affects consumer perception, with strong positive effects on perceived customization, convenience and usability, and negative effects on data privacy and product quality. Overall, the perception of DDPD is positive. Hedonic purchase motivations reduce the positive effects of DDPD, indicating a misalignment between DDPD and emotionally driven product characteristics. The findings advance theory and inform practitioners how to tailor DDPD strategies
Unmasking Disinformation: Enhancing Cyber Threat Intelligence through Crowdsourced Analysis and AI-Driven Training
Full text linkThe intersection of Artificial Intelligence (AI) and Cybersecurity holds immense potential but also presents significant challenges, particularly in collaborative and inter-organizational domains. This study explores the critical issue of disinformation in Cyber Threat Intelligence (CTI), focusing on its detection and mitigation through crowdsourced efforts and AI-driven approaches. By generating synthetic CTI datasets and orchestrating a collaborative detection campaign, the study reveals the vulnerabilities of both experts and laypersons to disinformation and the psychological biases that influence decision-making. Key findings highlight the critical role of education and training in improving human proficiency in identifying fake CTI and the transformative potential of AI in enhancing collaborative cybersecurity defenses. This research provides actionable insights into the use of AI for detecting disinformation, protecting collaborative AI systems, and fostering resilient inter-organizational cybersecurity strategies. The study contributes to advancing the cybersecurity domain by introducing a hybrid approach that combines human expertise, AI innovation, and collaborative resilience
How is Generative AI Transforming Content Creation on Social Media? An Exploratory Perspective on Human-AI Interaction Processes, Potentials and Pitfalls
Full text linkGenerative Artificial Intelligence (GenAI) presents a paradigm shift in social media content creation due to its unique ability to enhance media creation and aid in creative tasks. Creators have already put this into practice, and AI-augmented as well as AI-generated content is prevalent across platforms. However, the creators' perspective on how GenAI impacts social media content creation and its implications for the role of humans in the creation process remains poorly understood. Through 26 in-depth interviews, we employ an exploratory lens on human-GenAI interaction and its benefits and drawbacks in content creation. The results of thematic analysis shed light on the cooperative nature of human-GenAI interaction for ideation and the varying dynamics in the creation process, where the role of human creators changes from an executing force to verifying and controlling the actual media creation performed by GenAI
Mining Customer Journeys to Uncover Empirical Retail Agglomerations
Full text linkShopping centers are a cornerstone of the retail system, with their success hinging on offering tenant mixes and layouts that stimulate cross-shopping. Despite the rise of e-commerce, physical retail remains vital as consumers increasingly seek blended digital–in-store experiences. Yet, traditional approaches to analyzing shopper behavior often rely on surveys or simple frequency counts, which fail to capture the complexity of customer journeys. This study addresses this gap by applying spatial big data and unsupervised machine learning to investigate empirical retail agglomerations. The research explores how structured, non-random co-visitation patterns within a shopping center can be systematically identified and leveraged within a tenant-mix strategy. Drawing on 24 million anonymized visits to a major Canadian shopping center, the study employs GeoAI and association rule mining, specifically the Apriori algorithm, to uncover high-frequency and high-lift co-visitation rules. Results reveal structured journeys that highlight strong co-visitation between anchors and specialty tenants, confirming that shopping center behavior is far from random. These patterns suggest optimal adjacencies and provide a data-driven framework for leasing and tenant layout. The study contributes theoretically by extending retail agglomeration research using unsupervised methods to examine behavioral clustering on a large-scale dataset empirically. For practitioners, the research approach offers actionable insights for leasing and tenant-mix optimization
Reducing Cognitive Biases in Business Intelligence: A Framework for Objective Data Analysis
Full text linkThis paper examines the ways in which cognitive biases affect judgment in business intelligence (BI) settings. Drawing on bounded rationality theory, the study explores how human cognition, BI system design, and organizational pressure interact to produce biases such as anchoring bias and confirmation bias. Qualitative data were obtained from semi-structured interviews with representatives from two logistics companies. The results of a thematic analysis revealed that users frequently rely on heuristics because of time pressure, information overload, and visual design elements. While some informal bias-mitigation strategies exist, institutional support for them is limited. This study offers a framework for understanding and reducing cognitive bias in BI use, with implications for dashboard design, user training, and decision processes
AI, Uncertainty and Unethical Pro-Organizational Behavior (UPOB)
Full text linkUncertainty, unlike risk, cannot be analyzed using informed probabilities for alternative outcomes. Many pre-deployment technology outcomes are inherently uncertain, as is the case with generative AI. Such innovative developments are non-monotonic due to uncertainty, requiring design reconsiderations as new information emerges. Development teams must nevertheless weigh uncertain outcomes when deciding how to proceed. This paper introduces the concept of ‘Uncertain UPOB’ (U2POB) to distinguish behaviors where the unethical outcome is not guaranteed but remains possible due to uncertainty. Data was collected via a vignette-based survey of 101 technology professionals (606 decisions), with UPOB support found to be 22.1% higher under uncertain the conditions. Overall 35% of respondents were found to be supportive of at least one UPOB decision. Regression analyses indicated that subject UPOB propensity and personal responsibility psychometrics were predictive of UPOB behaviors in both the certain and uncertain contexts
Characterizing YouTube Channels via Multi-View Content Similarity
Full text linkYouTube channels communicate their themes and attract viewers through titles, descriptions, transcripts, and categories. While prior research has focused on user engagement, the internal consistency of content across a channel’s videos remains underexplored. This paper presents a framework for characterizing YouTube channels based on semantic similarity among key content features. Using a dataset of 150 channels and 157,235 videos, pairwise similarity scores were computed across six content feature combinations. five unsupervised clustering algorithms were applied to each pair, and results were integrated through majority voting to produce stable channel clusters. Similarity-based analysis revealed recurring alignment patterns, leading to five high-level content behavior characterizations. These profiles reflect distinct strategies in metadata coherence, narrative structure, and category usage. The proposed method enables scalable, label-free, and language-agnostic analysis of channel behavior. By revealing gaps between content and metadata, the framework surfaces potential editorial biases that may disproportionately affect marginalized audiences on social media
A Domain-Adaptive Soft Prompting Framework for Multi-Type Bias Detection in News
Full text linkAdvances in Large Language Models (LLMs) have enabled new opportunities to automate media analysis and improve collaborative social cybersecurity. A key task is bias detection in news reporting, which is essential for promoting information fairness and reducing polarization. However, existing approaches often rely on supervised fine-tuning with labeled datasets and fail to capture domain-specific linguistic patterns, limiting scalability and generalization. To address this, we propose a lightweight, modular framework that combines domain-adaptive pretraining (DAP) with Masked Language Modeling (MLM) and soft prompt tuning to detect six types of media bias (framing, group, semantic properties, connotation, informational spin, and phrasing). Our framework leverages 401,000+ New York Times articles from 2000 to 2024 to pretrain five LLMs, followed by bias prompting with small labeled data. The approach improves F1 by 7.6% and precision by 6.8% over hard prompts on average across the six types of biases. These results confirm DAP with soft prompts as an efficient and scalable solution for bias-aware NLP in resource-constrained environment