Search Results (793)

Today, data are no longer confined to numerical values arranged in row-by-column matrices or stored neatly within relational databases. One of the defining characteristics of big data is its high variety, encompassing unstructured and multimodal forms such as text, audio, images, and video. These data types dominate contemporary domains including social media, digital humanities, biomedical research, education, and surveillance systems. Yet these data types remain difficult to manage and analyze using traditional data management architectures. To cope with this shift, modern data management systems must move beyond schema-driven designs and incorporate multimodal artificial intelligence capable of understanding, integrating, and reasoning across heterogeneous data modalities. This article examines how multimodal AI, in particular large multimodal foundation models, can be leveraged to support the ingestion, representation, organization, and analysis of unstructured data. It discusses emerging multimodal data management frameworks, outlines a conceptual pipeline for multimodal data analysis, and highlights key challenges related to scalability, interpretability, and governance. By situating multimodal AI at the core of data management, this work argues that effective data analysis in the era of big data requires systems that treat meaning, context, and cross-modal relationships as first-class computational objects rather than afterthoughts. Full article

The use of artificial intelligence chatbots that mirror human interaction and emotional closeness has given rise to new forms of crime. Traditional online grooming is generally conceptualized as an offence in which a human perpetrator plans, initiates, and executes criminal conduct. However, the increasing involvement of artificial intelligence has introduced novel and complex scenarios. AI systems may either autonomously engage in conduct that facilitates the sexual exploitation of children or serve as tools that enhance, automate, or scale offenders’ activities. These developments challenge the traditional understanding of the offence and expose significant gaps in existing legal frameworks. Consequently, current regulatory approaches may prove inadequate to address the evolving nature of AI-assisted online grooming and associated forms of child sexual exploitation. This study investigates the case of grooming via social media using AI chatbots and discusses whether the current criminal legislation is sufficient to address this offence. Through a legal comparative method, this study examines the legal rules in the European Union, the United Kingdom, the United States, and China, focusing on the elements of criminal acts and criminal intent and the consideration of the liability of platform operators, developers, and deployers of AI systems. The study also discusses the problem of intermediary liability rules and less mature AI governance policies to tackle the fragmented and hidden nature of algorithmic actions. The study concludes that existing criminal law frameworks face significant challenges in addressing AI-assisted grooming, particularly regarding criminal intent, foreseeability, and liability allocation. The fragmentation of responsibility among offenders, platforms, and AI developers creates regulatory and enforcement gaps in the law. Accordingly, this study advocates for a risk-based liability framework, enhanced platform accountability, greater algorithmic transparency, and stronger child-centered safeguards. Full article

Effective sustainable environmental governance requires feedback between institutional risk management and lived public experience. We propose a hierarchical Topic–Aspect–Frame framework to compare pollution discourse across news and social media. Using 30,635 chunk-level Taiwanese Chinese texts collected from OpView Product Insight in May 2026, treated as an early summer one-month validation window, we analyze topic selection, aspect foregrounding, and frame-based risk construction. Category-balanced audits yielded conditional label precision among analyzable chunks of 91.3% for topics, 85.8% for aspects, and 90.1% for frames. Among 30,304 frame-eligible chunks, Governance/Regulation was more prevalent in news (gap = +4.47 pp; 95% CI = [+3.11, +5.88]), whereas Health and Lived Risk was more prevalent in social media (gap = −9.84 pp; 95% CI = [−10.68, −9.02]). Under the aspect-conditioned prototype design, sequential decomposition attributed the latter gap mainly to topic selection (−5.40 pp) and aspect foregrounding (−4.14 pp), with a smaller within-aspect component (−0.30 pp). Both core directions persisted across four fixed windows and 100 same-fraction subsamples. The framework offers a preliminary, auditable approach for identifying cross-media governance-experience mismatches, subject to seasonal, platform, denominator, and model-support constraints. Full article

With the widespread adoption of conversational artificial intelligence (Conv-AI), consumers have recently reshaped how they search, evaluate, and build relationships with brands. Accessibility and bidirectional communication have created a dynamic interface for the digital ecosystem. Yet despite a growing body of research, the field remains focused on productivity gains and the convenience of AI in digital commerce. But there is very little about how this Conv-AI intermediation affects the emotional aspect of consumer–brand love. This study draws on parasocial relationship theory and relationship marketing to advance the construct of parasocial displacement: the proposition that conversational AI agents do more than help consumers reach brands. They compete with brands for the consumer’s limited emotional attention. The authors test the proposition in three preregistered experiments (n = 791) set in realistic digital commerce scenarios. Study 1 (n = 212) shows that AI-mediated brand interactions reduce brand love compared with direct brand exposure, with the effect amplified when the AI agent presents a richer package of anthropomorphic social cues. Study 2 (n = 322) also finds that the effect passes through AI-induced parasocial attachment by careful attention and distraction. Study 3 (n = 257) demonstrates the moderation displacement of brand heritage, in which brands are largely protected, whereas emerging brands become vulnerable. This study extends parasocial theory from media personalities to algorithmic agents and proposes a triadic consumer–AI–brand framework. This triadic framework replaces the traditional dyadic models in AI-mediated branding activities. In practice, this framework identifies heritage brand equity as a relational buffer within the digital market ecosystem and proposes digital governance, disclosure for AI use, and agentic brand strategy. Full article

Gender-based violence may be considered a failure or absence of care across the interpersonal, symbolic, and structural levels. Feminist scholars have called for closer attention to an ethic of care as one vital pathway to shared solidarity for social justice and relations of non-violence. Works from Black, Indigenous, queer and disability writers and activists have similarly illustrated the transformative potential of collective care for building community and ending systems of oppression. In this paper, we draw on this critical literature to argue for framing collective care as both a practice and a long-term objective in work to prevent gender-based violence. To illustrate this framing, we share empirical data from two Australian studies: one with young people using social media to prevent gender-based violence, and one with prevention practitioners who work with men and boys. Our findings are organised around four central themes: care as collaboration; transformative care; a politic of care; and collective care in structural change. These findings represent patterns in practice, political approach, and imagined futures among our research participants that we suggest are reflective of ongoing commitments to empathy, compassion, and accountability. These patterns are substantively distinct from much mainstream programmatic and policy approaches to gender-based violence prevention, which often reproduce individualistic frames and are constrained by funding and governance models. We argue that violence prevention is fundamentally a shared project of collective care: supporting one another to recognise, interrogate, and challenge the gendered norms and structures that perpetuate gender-based violence. This work is inescapably relational, political, personal, and motivated by a shared sense of caring for each other. Full article

Fine-grained urban cultural perception is critical for GIScience, yet traditional social media studies struggle with complex cultural semantics and heterogeneous factor integration. Addressing Beijing’s “Capital Culture,” this study couples LLM agents with higher-order tensor decomposition. Using 2019 full-sample geotagged Sina Weibo data, we developed a four-agent collaborative architecture with Chain-of-Thought prompting and human-in-the-loop mechanisms via a locally deployed Qwen3-32B model. A four-way tensor (“Cultural Type–Evaluation Aspect–Sentiment Polarity–Spatial Carrier”) was constructed and integrated with kernel density estimation to characterize spatial differentiation. We address three questions: whether LLMs can reliably classify fine-grained cultural perceptions, how cultural types associate with evaluation dimensions, sentiments, and spatial carriers, and whether tensor decomposition reveals latent patterns beyond marginal frequencies. The agentic workflow achieves over 90% accuracy in cultural and sentiment classification, and the tensor decomposition attains a 94.87% goodness-of-fit, successfully identifying latent patterns. Spatially, Beijing’s capital culture exhibits an unbalanced hierarchical structure—“high coupling in the core area with differentiated expansion at the periphery.” This study validates the transition from “data-driven” to “AI + data dual-driven” spatial analysis, providing a quantifiable pathway for LLM-supported urban cultural governance. Full article

Social media have become central tools for government communication; however, they also present significant accessibility challenges for people with disabilities, particularly those with visual impairments. This study analyzes inclusive communication and digital accessibility practices in the official Facebook accounts of six Ecuadorian public institutions. A mixed-methods approach was employed, combining documentary analysis, a focus group with visually impaired users, and content analysis of 2429 Facebook posts published between 2023 and 2025. The analysis was conducted using four dimensions: propositional communication, copywriting, images, and videos. The results show that most publications only partially comply with accessibility criteria. While progress was identified in the use of clear and accessible language in textual content, significant deficiencies persist in multimedia content, particularly in the lack of alternative text, subtitles, and audio descriptions. The study concludes that inclusive communication in Ecuadorian public institutions remains fragmented and is not yet implemented as a cross-cutting public communication policy. Full article

This article examines the development of Catholic reflection on media, communication, and technology from nineteenth-century debates over press freedom to contemporary interventions on artificial intelligence. Drawing on a purposively selected corpus of Catholic documents issued at the universal level between 1832 and 2026, it combines historical–hermeneutical reconstruction, comparative document analysis, and juridical–institutional interpretation. The study distinguishes three heuristic phases: defensive regulation and the construction of Catholic media institutions; pastoral appropriation, dialogue, media education, and digital adaptation; and, since 2020, an anthropological deepening accompanied by growing concern with the political, economic, juridical, and social structures of AI. Particular attention is given to the Rome Call for AI Ethics, the two papal messages of 2024, Antiqua et nova, and Magnifica humanitas. The article argues that this history does not reveal an unchanged doctrine of human dignity, but a developing anthropological concern whose vocabulary, theological grounding, and normative function change over time. Earlier concerns with truth, moral order, ecclesial responsibility, and the salvation of souls are progressively reformulated through communication as communion, participation, rights, human agency, and integral human development. Full article

Amid the accelerated global transition toward sustainable electromobility, Chinese Electric Vehicles (EVs) have forged a complex, evolving communication ecosystem across overseas social media platforms. Conceptualizing global digital discourse as a complex adaptive system (CAS), this study integrates CAS theory with Competitive Framing theory to systematically elucidate the thematic configurations, framework dynamics, and ecological activation mechanisms underlying the international image of Chinese EVs. By integrating unsupervised BERTopic modeling, Large Language Model (LLM) semantic mapping, the Entropy Weight Method (EWM), and Social Network Analysis (SNA), this inquiry operationalizes a comprehensive computational communication framework to mine large-scale behavioral and textual data from YouTube. The empirical findings unveil that: (1) international audience perceptions have broken through the traditional “low-cost manufacturing” stereotype, spontaneously giving rise to a multidimensional, composite cognitive schema centered on smart ecosystems and design experiences; (2) driven by the interplay of rational and irrational user feedback loops, the ecological activation efficiencies across diverse discursive dimensions exhibit pronounced nonlinear variances, characterized by a “strong activation of intelligent ecosystems versus a long-tail stagnation of cost-effectiveness salience”; and (3) positive technological frameworks and negative geopolitical or regulatory risks engage in fierce, adversarial contestation and structural hybridization within a highly volatile network topology, culminating in a unique “dual-core” configuration. Theoretically, this study enriches the scholarly understanding of country-of-origin and corporate brand images through a complex systems lens; methodologically and practically, it offers a high-fidelity, actionable quantitative paradigm for global brand empowerment and targeted cross-border public opinion governance. Full article

Identifying the spatio-temporal evolutionary patterns and driving mechanisms of rural tourism network attention is essential for predicting the development trends of the rural tourism industry and delivering refined industrial governance. Taking 356 prefecture-level cities in China from 2015 to 2024 as basic research units, this paper constructs a comprehensive evaluation system for rural tourism network attention based on multi-source data. Furthermore, its spatio-temporal evolution characteristics and internal influencing factors are systematically investigated by means of spatial autocorrelation analysis and geographically weighted regression. The results indicate that the overall level of rural tourism network attention in China shows an obvious fluctuating growth trend, which can be divided into three successive stages, namely steady growth (from 0.8530 in 2015 to 1.2028 in 2019), explosive growth (from 1.9563 in 2020 to 3.7471 in 2021) and high-level fluctuation (maintained in the high range of 2.4–3.4). In addition, with the continuous iteration of internet communication media, the guiding influence of traditional search platforms has gradually weakened, while emerging social media and short-video platforms have become the core carriers of online tourism traffic. Correspondingly, media innovation persistently reshapes the spatial distribution pattern of rural tourism network attention. In terms of spatial characteristics, rural tourism network attention has undergone a significant transformation from geographical gradient polarization to overall regional equilibrium. Specifically, from 2015 to 2024, the overall Moran’s I index remained positive, with values ranging from 0.0116 to 0.1358, indicating an overall trend of gradual decline. High-attention areas are predominantly concentrated in economically developed urban agglomerations, whereas remote and economically underdeveloped regions exhibit contiguous low-value aggregation characteristics, which reveals a remarkable trend of balanced development nationwide. In view of driving mechanisms, highway network density, tourism income, rural tourism resource and enrollment of university students are identified as the core driving factors dominating the spatio-temporal evolution of rural tourism network attention. Moreover, the intensity of the influence of each factor presents distinct spatial heterogeneity. This study further reveals that the spatial heterogeneity of rural tourism network attention calculated using multi-source fused data shows a remarkable convergent characteristic, which can reflect the actual distribution of the rural tourism market more objectively and accurately. Meanwhile, rural tourism network attention is typically characterized by scale-dependent with the spatial distribution at the macro-scale being more balanced than that at the meso- and micro-scales. Full article

This study investigates the dynamics between media use, online activity, media literacy, and institutional trust among Indian citizens through a survey of adults distributed in six languages. Drawing on social capital theory, this study investigates how various media behaviors relate to perceptions of institutional actors such as governments, non-profits, and corporations as those actors increasingly seek digital avenues to reach constituencies. Findings underscore the significant relationships between media use, media literacy and positive views of democratic institutions, while online activities themselves did not appear to be significant. Notably, media literacy emerges as having a key positive tie to trust in political and state institutions as well as private, media, technology, and non-profit institutions. These results shed light on the nuanced relationship between digital engagement and perceptions of institutional credibility within the Indian context. Full article

As digital media become deeply embedded in postgraduate students’ daily learning and social interactions, online narratives of supervisor–postgraduate relationships have emerged as a crucial means for them to express authentic experiences and seek emotional support. Adopting a sensemaking perspective, this study employs online ethnography and thematic analysis to investigate postgraduate students’ narratives of supervisor–postgraduate relationships on a Douban group. The findings reveal four core thematic dimensions of these online narratives: identity formation, emotional interaction, experience sharing, and social connection. These dimensions help postgraduate students clarify their self-perception, release emotions, acquire practical experience, and establish a sense of group belonging, particularly in contexts where institutional support is insufficient. Online narratives essentially serve as a compensatory self-help channel for postgraduate students to cope with real-world challenges. They highlight structural shortcomings in offline supervisory governance and offer theoretical and practical insights to optimize supervisor–postgraduate relationships in the digital age. Full article

Environmental, social, and governance (ESG) risk is increasingly shaped by the relationships firms maintain within global supply chains. However, most ESG assessment approaches still treat firms as independent entities, overlooking how sustainability risks can spread across interconnected supplier–buyer networks. This study approaches ESG risk as a network-driven phenomenon rather than a purely firm-level outcome. Drawing on a large international dataset that combines supply-chain linkages, ESG incident data, and ESG-related news sentiment, the study examines whether incorporating network structure improves ESG risk assessment. The analysis integrates network-based econometric models with machine learning and graph-based approaches, and compares their performance with traditional firm-level models. The results show that ESG risk tends to cluster among connected firms, and that companies occupying central or intermediary positions within supply chains are more exposed to ESG incidents. In addition, negative ESG-related media sentiment provides an early signal of future ESG controversies. Models that explicitly account for network structure consistently outperform conventional approaches in both predictive accuracy and probability calibration. Thus far, the findings highlight the importance of considering supply-chain interdependencies when assessing ESG risk and demonstrate how network-based AI models can enhance the monitoring and prediction of sustainability risks in global production systems. Full article

This paper develops and evaluates a predictive analytics framework for influencer marketing return on investment (ROI), integrating hybrid deep learning architectures with trust-aware modelling to address the dual purpose of (a) developing a rigorous evaluation framework for influencer campaign performance and (b) examining the effectiveness of influencer marketing predictors. The concept of influencer marketing has quickly grown to be one of the most effective mediums within the contemporary digital advertising landscape. Due to the growing number of brands dedicating huge amounts of budgets to social media partnerships, the importance of data-driven approaches that can predict the outcomes of campaigns and, consequently, ensure the best possible return on investment (ROI) has become urgent. This paper introduces a machine learning system that can be used to forecast the sales of products promoted by influencer marketing campaigns based on campaign-level features, including type of platform, influencer type, type of campaign, time of the year, number of engagements, estimated reach, and campaign duration. A publicly available influencer marketing ROI dataset was trained and tested on an XGBoost regression model with a coefficient of determination ($R^2$) of 0.95 indicating high predictive power and generalization. The results show that engagement metrics and estimated reach are some of the most impactful factors in sales performance, and additional contextual factors like platform selection, type of campaign, and timing of the year also moderate results. In addition to predictive modelling, this paper explains how artificial intelligence (AI) can be strategically integrated throughout the influencer marketing lifecycle. With the inclusion of AI-based analytics, marketers will be able to leverage their intuitive decision-making processes with quantifiable and replicable measures and approaches that can lead to true consumer trust and lasting brand resonance. The framework proposed can provide practitioners and researchers with a scalable basis for implementing intelligent systems in the context of influencer marketing. Recent computer science research further demonstrates that AI-driven frameworks spanning generative content modelling, AI-powered CRM architectures for understanding consumer preferences on social media, and parasocial-trust models of influencer engagement provide strong methodological complements to the predictive approach developed here, while governance and project management considerations for deploying such systems are increasingly addressed in the literature. Concurrently, a growing body of influencer marketing research examines how platform affordances shape information-seeking and trust, how influencer attributes and social satisfaction mediate purchase intention, how influencer marketing drives sustainable consumption, and how social media measurably shapes health-related behaviours all of which motivate the predictive and trust-modelling objectives of this work. Full article

Identifying sparse, context-dependent target discourse such as ethical risk discourse on generative AI in noisy social media data is a long-standing challenge in computational text analysis. Beyond classification, interpreting the resulting topic structure transparently poses an additional methodological challenge. To address these problems, this study proposes a reproducible two-stage framework. First, four LLMs (GPT-4.1, GPT-3.5-turbo, Claude Sonnet 4.6, and Gemini 2.5 Pro) are compared on a human-annotated validation set using a zero-shot prompt grounded in five ethical risk categories, and the best-performing model is selected to classify the full keyword-prescreened corpus. Validity is evaluated against human annotations and supervised baselines. Second, BERTopic is applied to the classified corpus, and sub-topics are linked to higher-level categories through an explicit mapping protocol. The study draws on approximately 500,000 ChatGPT-related English-language tweets from January to March 2023. Only 36.4% of the validation sample constituted ethical risk discourse, confirming substantial pre-screening noise. GPT-4.1, selected as the final classification model, achieved the strongest performance (accuracy = 0.899, F₁ = 0.859, Cohen’s κ = 0.780), significantly outperforming conventional supervised baselines. BERTopic yielded 33 non-outlier sub-topics; within this subset, Societal and democratic risks (36.16%) and Technical safety (20.90%) were the largest categories. These findings should be interpreted not as a direct measure of users’ risk perceptions in 2023, but as the category distribution within the structured subset excluding outliers, after keyword screening and classification under the current ethical risk taxonomy used in this study. Within this scope, societal and institutional concerns were at least as prominent as those related to technical failures. Full article