Search Results (278)

Existing approaches to social media sentiment analysis typically focus on static classification, offering limited foresight into how public opinion evolves. This study addresses that gap by introducing the Multi-Feature Sentiment-Driven Forecasting (MFSF) framework, a novel pipeline that enhances sentiment trend prediction by integrating rich contextual information from text. Using state-of-the-art transformer models on the Sentiment140 dataset, our framework extracts three concurrent signals from each tweet: sentiment polarity, aspect-based scores (e.g., ‘price’ and ‘service’), and topic embeddings. These features are aggregated into a daily multivariate time series. We then employ a SARIMAX model to forecast future sentiment, using the extracted aspect and topic data as predictive exogenous variables. Our results, validated on the historical Sentiment140 Twitter dataset, demonstrate the framework’s superior performance. The proposed multivariate model achieved a 26.6% improvement in forecasting accuracy (RMSE) over a traditional univariate ARIMA baseline. The analysis confirmed that conversational aspects like ‘service’ and ‘quality’ are statistically significant predictors of future sentiment. By leveraging the contextual drivers of conversation, the MFSF framework provides a more accurate and interpretable tool for businesses and policymakers to proactively monitor and anticipate shifts in public opinion. Full article

Floods pose a growing threat globally, causing tragic loss of life, billions in economic damage annually, and disproportionately affecting socio-economically vulnerable populations. This paper aims to improve flood-risk communication for community leaders by exploring the application of artificial intelligence. We categorize U.S. flood information sources, review communication modalities and channels, synthesize the literature on community leaders’ roles in risk communication, and analyze existing technological tools. Our analysis reveals three key challenges: the fragmentation of flood information, information overload that impedes decision-making, and the absence of a unified communication platform to address these issues. We find that AI techniques can organize data and significantly enhance communication effectiveness, particularly when delivered through infographics and social media channels. Based on these findings, we propose FLAI (Flood Language AI), an AI-driven flood communication platform that unifies fragmented flood data sources. FLAI employs knowledge graphs to structure fragmented data sources and utilizes a retrieval-augmented generation (RAG) framework to enable large language models (LLMs) to produce contextualized narratives, including infographics, maps, and cost–benefit analyses. Beyond flood management, FLAI’s framework demonstrates how AI can transform public service data management and institutional AI readiness. By centralizing and organizing information, FLAI can significantly reduce the cognitive burden on community leaders, helping them communicate timely, actionable insights to save lives and build flood resilience. Full article

This study presents a computational analysis of industry-specific advertising message strategies through the theoretical lens of the FCB (Foote, Cone & Belding) grid framework. Leveraging the AiSAC (AI Analysis System for Ad Creation) system developed by the Korea Broadcast Advertising Corporation (KOBACO), we analyzed 27,000 Korean advertisements across five major industries using advanced machine learning techniques. Through Latent Dirichlet Allocation topic modeling with a coherence score of 0.78, we identified five distinct message strategies: emotional appeal, product features, visual techniques, setting and objects, and entertainment and promotion. Our computational analysis revealed that each industry exhibits a unique “message strategy fingerprint” that significantly discriminates between categories, with discriminant analysis achieving 62.7% classification accuracy. Time-series analysis using recurrent neural networks demonstrated a significant evolution in strategy preferences, with emotional appeal increasing by 44.3% over the study period (2015–2024). By mapping these empirical findings onto the FCB grid, the present study validated that industry positioning within the grid’s quadrants aligns with theoretical expectations: high-involvement/think (IT and Telecom), high-involvement/feel (Public Institutions), low-involvement/think (Food and Household Goods), and low-involvement/feel (Services). This study contributes to media science by demonstrating how computational methods can empirically validate the established theoretical frameworks in advertising, providing a data-driven approach to understanding message strategy patterns across industries. Full article

A growing knowledge base highlights the importance of accounting for a variety of social and structural determinants of health (SDOH) when understanding mental and behavioral health among adolescents and young adults. The objective of the current study is to examine patterns of self-reported SDOH deficits and characterize participant health indicators and social identity across classes. Data is from a cross-sectional national study of young people who were recruited through study advertisements on social media and surveyed online. Data were collected between June 2022 and October 2023. Eligibility included (1) ages 13–22 years, (2) living in the United States, and (3) proficient in English. Health indicators included suicide attempts, suicidal ideation, drug overdose, perceived likelihood of living to age 35, non-suicidal self-injury, recent alcohol use, and depression. Five classes of SDOH deficits were identified: (1) Economic Instability, (2) Low Overall SDOH Deficits, (3) High Social SDOH Deficits (adversity and discrimination), (4) High Economic SDOH Deficits, and (5) High Overall SDOH Deficits. Differences across class by health indicators and marginalized identity were found, with high proportions of gender minority and sexual minority youth in both the High Overall SDOH Deficit group and the High Social SDOH Deficit classes. Black youth were more likely to be part of the High Economic SDOH Deficits class. The findings encourage a public health approach that recognizes that improving the health of today’s young people must be connected to policies that reduce poverty, improve neighborhoods, and increase access to basic goods, services, and healthcare. Full article

The Brazilian population in the United States is growing, and many Brazilian workers are employed in settings that may lack occupational health and safety (OHS) protections. In this study, we examined two domains of OHS (measured by the Occupational Health and Safety Vulnerability Survey), namely, Workplace Hazards (potential dangers that may result in injury or illness) and Workplace Vulnerability (inadequate occupational health and safety resources), and described health and demographic characteristics associated with these conditions. Eligible participants were women aged 18 and over, born in Brazil, currently residing in the United States, and employed. A cross-sectional online survey was conducted between July and August 2020. Recruitment occurred through community partnerships and social media. Multivariable models among n = 191 women revealed that greater exposure to Workplace Hazards was associated with employment in private household settings, including childcare and housecleaning (p < 0.001). The association between Workplace Vulnerability and jobs in private household services approached statistical significance (p = 0.07). Both Workplace Hazards and Workplace Vulnerability were associated with lower incomes and educational attainment, as well as having public insurance. Our findings suggest the need for stronger OHS protections and policies, particularly among those working in private household services, to ensure safer working conditions for Brazilian immigrant women. Full article

While digital transformation in e-commerce receives the most publicity, applications in energy and water utilities have been ongoing for decades. Using a methodology based on a systematic review, the paper offers a model of how it occurs in water utilities, reviews experiences from the field, and derives lessons learned to create a road map for future research and implementation. Innovation in water utilities occurs more in the field than through organized research, and utilities share their experiences globally through networks such as water associations, focus groups, and media outlets. Their digital transformation journeys are evident in business practices, operations, and asset management, including methods like decision support systems, SCADA systems, digital twins, and process optimization. Meanwhile, they operate traditional regulated services while being challenged by issues like aging infrastructure and workforce capacity. They operate complex and expensive distribution systems that require grafting of new controls onto older systems with vulnerable components. Digital transformation in utilities is driven by return on investment and regulatory and workforce constraints and leads to cautious adoption of innovative methods unless required by external pressures. Utility adoption occurs gradually as digital tools help utilities to leverage system data for maintenance management, system renewal, and water loss control. Digital twins offer the advantages of enterprise data, decision support, and simulation models and can support distribution system optimization by integrating advanced metering infrastructure devices and water loss control through more granular pressure control. Models to anticipate water main breaks can also be included. With such advances, concerns about cyber security will grow. The lessons learned from the review indicate that research and development for new digital tools will continue, but utility adoption will continue to evolve slowly, even as many utilities globally are too stressed with difficult issues to adopt them. Rather than rely on government and academics for research support, utilities will need help from their support community of regulators, consultants, vendors, and all researchers to navigate the pathways that lie ahead. Full article

Background: Obesity is a chronic and complex disease; by its nature, it represents an enormous challenge to be solved and managed. For that matter, several guidelines have been published, but there is still a long way to go until concrete scaled results can be presented. Adults with obesity, and especially severe obesity, need to have access to treatment programs, but they are not available for the vast majority of the population. Objective: The aim of this study is to evaluate the effectiveness of a multidisciplinary treatment program for obesity (MTPO) offered to adults (ages 18 to 50 years old) with a BMI over 30 kg/m². Methods: Participants were invited through media ads, resulting in 404 participants for the first phase of that study, from whom the risk profile was assessed. After that, 180 participants (82.8% with severe obesity) concluded the MTPO, which consisted of 48 sessions of exercises and the same number of professional orientations about a healthy lifestyle, including the importance of being physically active, how to improve their eating habits, and how to control their emotions. Results: For the analysis of results, participants were grouped according to their weight loss in terciles, with the first, tercile presenting an average weight loss of 7.6%, which is considered clinically significant. In the same way, the average percental variations were even higher in this group for body fat (12.7%) and the lean mass to fat mass ratio (LM/FM), which increased by 14.3%. The homeostatic model assessment for insulin resistance, HOMA-IR, was around 3 times the variation of body mass, whereas the triglycerides (TG) and the hemoglobin A1C (H1Ac) were around twice that rate. Conclusions: These results made clear the effectiveness of the MTPO, which needs to be tested in public health services. Full article

Draining wetland landscapes accelerates climate change, and multilateral support is therefore needed to speed up the transition to new land uses. This paper examines perceptions of ecosystem services (ES) in wetland areas in scientific and civic assessments. The case study area is Denmark’s largest drained wetland system, which is notable for its carbon sequestration potential. The area’s transformation efforts involving public participation offer a unique chance to examine differences between scientific and civic perceptions of ES. This exceptional case is ideal for revealing contextual differences, trade-offs, and controversies between scientific and civic perceptions of ES. Millennium ES Assessment and CICES are used as a conceptual framework for understanding and mapping human–nature interactions in a nature park. However, these systems are, in practice, not sufficiently developed to identify how citizens understand and value ES in real life. Therefore, we analyse perceptions using interviews, collaborative mapping, and media analysis. We compare these to scientific ES mappings based on local data, literature reviews, and fieldwork. The paper concludes that (1) scientific ES asymmetries are important; (2) environmental blind spots in scientific ES are due to its approach to knowledge collection; (3) citizens’ blind spots are due to their everyday life focus and tabooing the issue of local climate mitigation; and (4) science-based ES assessments and accounts are disconnected from local ES controversies. We argue that identifying ES controversies through various scientific methods may improve climate mitigation and restoration efforts if community planning becomes involved. Full article

This paper presents a structured methodology for identifying and addressing key communication challenges in the forestry sector, using the Czech Republic (CZ) as a case study. The approach integrates the CIMO model, problem tree analysis, SWOT evaluation, and a confrontation matrix to identify critical factors influencing communication challenges and prioritize strategic responses. Findings from a representative public survey (n = 3600), participatory workshops, and expert consultations indicate that the primary challenge (C) in Czech forestry is a fragmented sector facing declining trust and minimal media presence. The proposed intervention (I) is a unified, strategic communication methodology designed to activate the mechanism (M) of shared narratives and coordinated messaging. This approach aims to achieve the desired outcomes (O): increased trust, engagement, and legitimacy. The absence of a unified, long-term communication strategy contributes significantly to public misunderstanding, erodes trust, and limits policy support. The study proposes evidence-based tools to enhance sector visibility, coherence, and public engagement. With direct payments for ecosystem services under debate in CZ, effective communication is a prerequisite for securing public and political support. The methods employed have broader relevance for forestry in other countries seeking strengthened stakeholder alignment through strategic communication. Full article

In an era of increasing global uncertainty, tourism destinations face significant challenges due to political instability and social unrest, which shape travelers’ perceptions and decision making. This study examines the relationship between perceived risk, resilience, and destination choice, focusing on the extent to which political and social conditions influence travel intentions. Using the social amplification of risk framework (SARF) and a quantitative survey, this research identifies key determinants of tourism resilience and risk perception management. Our findings indicate that political instability, safety concerns, and negative media coverage deter travelers, while effective crisis communication, strong governance, and high-quality public services can enhance a destination’s appeal. Based on these findings, the study recommends that destination marketers and tourism policymakers invest in targeted safety communication, service quality improvements, and strategies that address the specific concerns of more risk-sensitive demographics, such as women. The study offers strategic insights for destination marketers, tourism policymakers, and hospitality stakeholders on how to mitigate perceived risks and foster resilience in tourism-dependent economies. Future research could explore cross-cultural traveler behavior and incorporate perspectives from tourism professionals to further inform resilience strategies. By addressing these challenges, destinations can develop sustainable strategies to navigate crises and maintain competitiveness in an unpredictable global landscape. Full article

The various definitions of academic freedom in the United States reflect the influence of social and political norms in its interpretation as both a professional and legal right. Yet, underlying these interpretations is the operational understanding, which includes both legal and professional considerations, that academic freedom is a widely recognized principle that grants professors the autonomy and authority to explore intellectual questions within their academic disciplines, conduct professional work, and express their views in the public sphere without undue interference or suppression. In other words, academic freedom is a foundational principle rooted in legal and institutional frameworks that safeguards professors’ ability to engage in intellectual inquiry, professional practice, and public discourse without undue interference. This principle extends beyond mere professional courtesy. It is recognized as essential to the functioning of higher education institutions and the broader democratic exchange of ideas. The public (including policymakers, industry leaders, media, and students) generally acknowledges academic freedom as an inherent protection that protects from unjustified interferences. By doing so, professors can participate in governance, disciplinary leadership, and extramural activities without the fear of retaliation or coercion. By insulating academic work from ideological, political, or economic constraints, academic freedom maintains the legitimacy and independence of scholarly inquiry in service to both knowledge advancement and the public good. Full article

The rapid evolution of autonomous vehicles (AVs) has ignited widespread interest in their potential to transform mobility and transportation ecosystems. However, despite significant technological advances, the acceptance of AVs by the public remains a complex and multifaceted challenge. This state-of-the-art review explores the key factors influencing AV acceptance, focusing on the intersection of artificial intelligence (AI) services, user experience, social dynamics, and regulatory landscapes across diverse global regions. By analyzing trust, perceived safety (PS), cybersecurity, and user interface design, this paper delves into the psychological and behavioral drivers that shape public perception of AVs. It also highlights the role of demographic segmentation and media influence in accelerating or hindering adoption. A comparative analysis of AV acceptance across North America, Europe, Asia, and emerging markets reveals significant regional variations, influenced by regulatory frameworks, economic conditions, and social trends. Also, this review reveals critical insights into the perceived safety associated with AV technology, including legal uncertainties and cybersecurity concerns, while emphasizing the future potential of AVs in urban environments, public transit, and autonomous logistics fleets. This review concludes by proposing strategic roadmaps and policy implications to accelerate AV adoption, offering a forward-looking perspective on how advances in technology, coupled with targeted industry and government initiatives, can shape the future of autonomous mobility. Through a comprehensive examination of current trends and challenges, this paper provides a foundation for future research and innovation aimed at enhancing public acceptance and trust in AVs. Full article

In recent years, large-scale wildfires have become a serious threat to terrestrial ecosystems and people in the Chiquitania region of Bolivia. Understanding public perceptions is fundamental to designing comprehensive and effective wildfire management strategies. The objectives of the study were to learn perception on the main causes of wildfires, to understand their perceptions of the impacts of these events, and to explore the most viable solutions to preventing future wildfires in the Chiquitania region of Bolivia. We developed a 15-questions online survey and disseminated it through social media platforms, mobile messaging service groups, and at two workshops held in two locations. A total of 597 people participated in the survey with a balanced sex distribution. The participants were mainly young people aged 18–24 (45.40%) and 25–34 (21.40%), representing university students (42.6%) and professionals (42.6%). The data came from seven departments, but Santa Cruz was more strongly represented (75.9%). In addition, although only 65% considered themselves part of the general population, the data shows that 76% had personal experience of wildfires. Respondents indicated that fires were caused by human activities (95.9%), mainly due to traditional agricultural practices. The most important perceived impacts included landscape and vegetation quality, fauna habitat and ecosystem regeneration. In addition, participants have prioritized the reinforcement of patrols and surveillance, the hiring of forest firefighters and the purchase of aerial firefighting units. For prevention, the most chosen was to change policies that promote fires, changing the vision for economic development and stricter penalties. The findings can be used to formulate public policies aimed at preventing wildfires, mitigating their impacts and promoting environmental conservation. Full article

Social media (SM) platforms allow users to communicate rapidly, exchange information, and create and share real-time content. Currently, 4.5 billion people use social media worldwide, making it an influential part of daily life. Beyond information sharing, social media facilitates communication, transfers information, and serves as a platform for advertising and shaping public opinion. Researchers analyse these aspects to understand and describe societal realities. The primary purpose of this paper is to analyse social media’s impact on global research. The research included an analysis of the most popular social platforms, considering the number of Web of Science (WoS) articles relating to them and the year in which the platform was established or the Monthly Active Users (MAU) factor. Data were collected based on the WoS database in the topic (which contains texts of title, abstract, author keywords, and Keywords Plus) of the articles, where phrases containing names of SM platforms were used. Quantitative research is a type of research that analyses data numerically to find relationships and statistical regularities of searched phrases. The impact of social media on the dissemination of research and findings was analysed based on the results of the study and also on the literature data. This research reveals a lack of correlation between the number of articles indexed in the WoS and the MAU of individual social media platforms. This observation raises an important question: do social media researchers focus on studying the platforms used by the majority, thereby providing a more accurate representation of current social dynamics? This article is helpful for researchers, policymakers, and social media platform developers seeking to understand the role of social media in shaping modern communication and public discourse. The most important finding of the paper is the low correlation between the number of SM users and the impact of social media platforms on learning, as exemplified by the Twitter (Note: Twitter was an American social networking service rebranded as X in 2023. As the period of data analysed in this paper covered the years up to 2022, the authors decided to stay with the name Twitter) platform, which is the 17th largest SM platform but is the 2nd (after Facebook) in implications for science. Full article

TikTok is a popular social media platform offering educational opportunities for health issues such as rheumatic fever, which primarily affects 4–19-year-olds globally. This content analysis aimed to explore the type of rheumatic fever content available and popular on TikTok and the role that rheumatic fever representation may play in shaping public understanding and attitudes. The top 100 TikTok video posts under the hashtag #rheumaticfever were examined. Descriptive statistics were used to summarize video metrics and deductive thematic analysis enabled the coding of video content. The majority of TikTok users creating rheumatic fever content were patients or family members of people suffering from rheumatic fever (42%), followed by health professionals (30%). Forty-three percent of videos had negative connotations and personal stories were the most commonly coded type of video (42%). In terms of rheumatic fever content, symptoms (n = 59), medications/treatment (n = 37) and disease pathogenesis (n = 36) were the most common themes. Misinformation was identified in 3% of videos. This study provides a unique insight into who is making rheumatic fever-related content on TikTok and the primarily negative framing of narratives people are exposed to. There are opportunities for future health promotion strategies to focus on the gaps identified in this study, including information on where to seek health services, primordial prevention and stories of recovery. Full article