Search Results (197)

Social media platforms have emerged as valuable sources for mental health research, enabling the detection of conditions such as depression through analyses of user-generated posts. This manuscript offers practical, step-by-step guidance for applying machine learning and deep learning methods to mental health detection on social media. Key topics include strategies for handling heterogeneous and imbalanced datasets, advanced text preprocessing, robust model evaluation, and the use of appropriate metrics beyond accuracy. Real-world examples illustrate each stage of the process, and an emphasis is placed on transparency, reproducibility, and ethical best practices. While the present work focuses on text-based analysis, we discuss the limitations of this approach—including label inconsistency and a lack of clinical validation—and highlight the need for future research to integrate multimodal signals and gold-standard psychometric assessments. By sharing these frameworks and lessons, this manuscript aims to support the development of more reliable, generalizable, and ethically responsible models for mental health detection and early intervention. Full article

This article explores the integration of artificial intelligence (AI) in digital marketing through social and mobile networks and its role in fostering sustainable consumer behavior. AI enhances personalization, sentiment analysis, and campaign automation, reshaping marketing dynamics and enabling brands to engage interactively with users. A quantitative study conducted on 501 social media users evaluates how perceived benefits, risks, trust, transparency, satisfaction, and social norms influence the acceptance of AI-driven marketing tools. Using structural equation modeling (SEM), the findings show that social norms and perceived transparency significantly enhance trust in AI, while perceived benefits and satisfaction drive user acceptance; conversely, perceived risks and negative emotions undermine trust. From a sustainability perspective, AI supports the efficient targeting and personalization of eco-conscious content, aligning marketing with environmentally responsible practices. This study contributes to ethical AI and sustainable digital strategies by offering empirical evidence and practical insights for responsible AI integration in marketing. Full article

Health professionals and institutions, as users and influencers, use social networks to disseminate information and knowledge about health issues, in the case of organ donation and transplantation (ODT) to spread the social benefits of the process and increase the positive attitude towards ODT. The aim of this work was to analyse the perception and use of social networks by university students of health sciences to determine whether, in their opinion, social platforms are suitable for the promotion of ODT after participating in an educational programme specialising in ODT and communication. The students indicated that social networks are a good medium for disseminating messages about ODT, with WhatsApp standing out as the most appropriate after the programme. Eighty-six per cent say that social media can positively influence the attitude towards ODT and 65% have started to follow ODT institutional accounts on social media. Addressing communication in specialisation programmes in the field of health and ODT raises awareness of the responsible use of social media among university health students and strengthens their capacity as prescribers of the social benefits of ODT. Full article

Amid the rapid growth of social media and live streaming platforms, streamers, who serve as a crucial link between products and users, have garnered significant attention from both academia and industry. This study explores the impact of the streamer’s social capital (S) on user stickiness (R), as well as the mediating roles of perceived value and flow experience (O) in light of the Stimuli-Organism-Response (SOR) framework and social capital theory. A total of 322 valid samples were analyzed through Structural Equation Modeling (SEM) and Fuzzy-set Qualitative Comparative Analysis (fsQCA). The results from the SEM indicate that the structural capital, cognitive capital, and relational capital of streamers in e-commerce live streaming significantly influence users’ perceived value, while structural capital and relational capital substantially impact users’ flow experience. Furthermore, both perceived value and flow experience are found to have a significant effect on user stickiness, with chained mediating effects observed between perceived value and flow experience. The fsQCA results further identify three configurational paths influencing user stickiness: the perceived value-oriented path, the flow experience-oriented path, and a hybrid path. This study offers valuable insights and practical implications for e-commerce merchants and companies involved in live streaming activities. Full article

Social media have been fundamental in the daily lives of millions of people, but they have raised concerns about content moderation policies, the management of personal data, and their commercial exploitation. The acquisition of Twitter (now X) by Elon Musk in 2022 generated concerns among Twitter users regarding changes in the platform’s direction, prompting a migration campaign by some user groups to the federated network Mastodon. This study reviews the onboarding of users to this decentralised platform between 2016 and 2022 and analyses the migration of 19,000 users who identified themselves as supporters of the platform switch. The results show that the migration campaign was a reactive response to Elon Musk’s acquisition of Twitter and was led by a group of highly active academics, scientists, and journalists. However, a complete transition was not realised, as users preferred to straddle their presence on both platforms. Mastodon’s decentralisation made it difficult to exactly replicate Twitter’s communities, resulting in a partial loss of these users’ social capital and greater fragmentation of these user communities, which highlights the intrinsic differences between both platforms. Full article

Social media platforms have been recognized as significant contributors to the dissemination of polarizing content, the spread of disinformation, and the proliferation of far-right populist discourse. While certain political actors deliberately seek to disseminate disinformation, a more nuanced understanding is necessary to elucidate why users consume and accept this biased content. Using data from over 120,000 participants across five European and Spanish surveys, we empirically examined the relationships between social media use, disinformation, false news, users’ digital agency, far-right ideology, and far-right voting. We postulated that a lack of users’ digital agency is a significant contributor to this phenomenon and found a significant association between users’ low digital agency and the adoption of far-right ideologies (odds ratio [OR] = 1.16, 95% confidence interval [CI] 1.08–1.23). This association remained after controlling for trust in social media news, psychological and social factors, sociodemographic variables, and response bias. Full article

The rapid development of e-commerce has brought unprecedented opportunities for small and medium-sized enterprises (SMEs), particularly those in the retail sector. WeChat e-commerce, which combines the advantages of social media and e-commerce, offers SME retailers an accessible and efficient e-commerce solution. As market competition intensifies, user retention has become crucial for their success in WeChat e-commerce. This study extended the Expectation Confirmation Model (ECM) by incorporating perceived quality and privacy calculus to examine users’ continuance intention towards WeChat e-commerce for SME retailers. A total of 694 valid responses were collected from users with prior experience using WeChat e-commerce offered by SME retailers, and the proposed model was validated using structural equation modeling. The results indicated that the trade-off between privacy concerns and perceived benefits significantly affected users’ intention to continue using WeChat e-commerce. Moreover, the information quality and service quality dimensions were found to directly or indirectly influence this continuance intention towards WeChat e-commerce via privacy concerns, perceived benefits, and confirmation. In conclusion, this study provides insights for further research on continuance intention in WeChat e-commerce and suggestions for SMEs to formulate e-commerce strategies. Full article

The rapid development and deployment of artificial intelligence (AI) technologies have sparked intense public interest and debate. While these innovations promise to revolutionise various aspects of human life, it is crucial to understand the complex emotional responses they elicit from potential adopters and users. Such findings can offer crucial guidance for stakeholders involved in the development, implementation, and governance of AI technologies like OpenAI’s ChatGPT, a large language model (LLM) that garnered significant attention upon its release, enabling more informed decision-making regarding potential challenges and opportunities. While previous studies have employed data-driven approaches towards investigating public reactions to emerging technologies, they often relied on sentiment polarity analysis, which categorises responses as positive or negative. However, this binary approach fails to capture the nuanced emotional landscape surrounding technological adoption. This paper overcomes this limitation by presenting a comprehensive analysis for investigating the emotional landscape surrounding technology adoption by using the launch of ChatGPT as a case study. In particular, a large corpus of social media texts containing references to ChatGPT was compiled. Text mining techniques were applied to extract emotions, capturing a more nuanced and multifaceted representation of public reactions. This approach allows the identification of specific emotions such as excitement, fear, surprise, and frustration, providing deeper insights into user acceptance, integration, and potential adoption of the technology. By analysing this emotional landscape, we aim to provide a more comprehensive understanding of the factors influencing ChatGPT’s reception and potential long-term impact. Furthermore, we employ topic modelling to identify and extract the common themes discussed across the dataset. This additional layer of analysis allows us to understand the specific aspects of ChatGPT driving different emotional responses. By linking emotions to particular topics, we gain a more contextual understanding of public reaction, which can inform decision-making processes in the development, deployment, and regulation of AI technologies. Full article

Fashion live commerce has rapidly emerged as a compelling format that blends entertainment, real-time interaction, and product promotion. However, limited research has examined how specific experiential and perceptual factors influence consumer behavior in this context. This study aims to identify the key psychological and environmental drivers of satisfaction, continued platform use, and purchase intention among viewers of fashion live commerce. Using the stimulus–organism–response framework, this research focuses on the effects of perceived credibility, social media influencer characteristics, informativeness, internal shop environment, and monetary savings. Data were collected from 300 users of fashion live commerce platforms and analyzed using partial least squares structural equation modeling (PLS-SEM). The results indicate that all predictor variables significantly influence either satisfaction or current use, and both satisfaction and current use significantly predict purchase intention. Among the factors, satisfaction plays a central role, acting as a strong predictor for both current engagement and future buying decisions. These findings offer theoretical insights into consumer engagement in live commerce and provide practical guidance for streamers, marketers, and platform designers aiming to improve user experience and conversion rates. This study contributes to understanding the evolving dynamics of digital shopping environments shaped by social and emotional interactions. Full article

This paper critically examines the risks to democratic institutions and practices posed by disinformation, echo chambers, and filter bubbles within contemporary social media environments. Adopting a modern republican approach and its conception of liberty as nondomination, this paper analyzes the role of algorithms, which curate and shape user experiences, in facilitating these challenges. My argument is that the proliferation of disinformation, echo chambers, and filter bubbles constitutes forms of domination that manipulate vulnerable social media users and imperil democratic ideals and institutions. To counter these risks, I argue for a three-pronged response that cultivates robust institutional and individual forms of antipower by regulating platforms to help protect users from arbitrary interference and empower them to fight back against domination. Full article

Earthquakes are sudden-onset disasters requiring rapid, accurate information for effective crisis response. Social media (SM) platforms provide abundant geospatial data but are often unstructured and produced by diverse users, posing challenges in filtering relevant content. Traditional content filtering methods rely on natural language processing (NLP), which underperforms with mixed-language posts or less widely spoken languages. Moreover, these approaches often neglect the spatial proximity of users to the event, a crucial factor in determining relevance during disasters. This study proposes an NLP-free model that assesses the spatial credibility of SM content by analysing users’ spatial trajectories. Using earthquake-related tweets, we developed a machine learning-based classification model that categorises posts as directly relevant, indirectly relevant, or irrelevant. The Random Forest model achieved the highest overall classification accuracy of 89%, while the k-NN model performed best for detecting directly relevant content, with an accuracy of 63%. Although promising overall, the classification accuracy for the directly relevant category indicates room for improvement. Our findings highlight the value of spatial analysis in enhancing the reliability of SM data (SMD) during crisis events. By bypassing textual analysis, this framework supports relevance classification based solely on geospatial behaviour, offering a novel method for evaluating content trustworthiness. This spatial approach can complement existing crisis informatics tools and be extended to other disaster types and event-based applications. Full article

Destination Management Organizations (DMO) increasingly harness social media to foster favorable online destination brand experiences (ODBEs) during travelers’ pre-trip planning. However, empirical knowledge about such experiences in ecotourism contexts remains limited. This study addresses the gap by proposing and validating an ODBE measurement scale adapted to ecotourism destinations. An online questionnaire was administered to Facebook users following seven certified Romanian ecotourism destinations, yielding 281 valid responses. Through exploratory factor analysis and confirmatory composite analysis, the scale was refined into three components—hedonic, utilitarian, and spatio-temporal—capturing emotional immersion, rational evaluation, and destination-specific spatial perceptions. Structural equation modeling further demonstrated that ODBEs exert a strong, positive effect on two key behavioral intentions: visiting the destination (β = 0.913) and sharing destination information online (β = 0.875). This study advances theories on tech-mediated pre-travel experiences by emphasizing nature and local culture. The findings provide DMOs with practical guidance for creating effective social media content to enhance destination branding and support sustainable tourism. Full article

Objective: Protein supplements (PSs) are widely consumed by professional and non-professional athletes, yet research on non-athletic PS users’ perceptions, motivations, and health risk awareness is limited. This study aimed to investigate non-professional athletes’ PS patterns of use, motivations, and safety. Methods: A cross-sectional study was conducted using a constructed questionnaire reporting on PS usage trends, exercise habits, and demographic factors. Adult respondents were recruited from gyms, athletic organizations, amusement parks, and playing fields. Results: We received 1100 responses, and 327 were PS users. From the total of PS users, there was a prevalence of PS use in males [(203 (62%)]; adults in the age group of 25–34 [136 (42%)], p < 0.001; and participants with a normal BMI (189, 58%), p < 0.001. Following high-intensity fitness exercise sessions and engagement with more than two types of physical activity were associated with more than doubled odds of PS consumption (p < 0.001). The main reasons for PS intake were for muscle mass increase (35%) and recovery (18%), and protein powder was the most popular PS (279; 64%). The main channels of information for PS use were Web/social media (50, 40%) and coaches (54, 43.2%), while one out of two [35 (49%); p = 0.008] of those engaged in more than two types of physical exercise declared that PSs are good for health. Conclusion: The findings highlight demographic, behavioral, and informational factors shaping PS consumption in non-professional athletes. Despite the perceived benefits, reliance on non-expert sources and unregulated products raises concerns about consumer awareness and safety, while educational initiatives to promote evidence-based supplementation practices are deemed crucial. Full article

The growing use of social media data has opened new avenues for understanding user perceptions and operational inefficiencies in transportation systems. Among the most widely adopted analytical approaches for extracting insights from these data are sentiment analysis and topic modeling, which enable researchers to capture public opinion trends and uncover latent themes in unstructured content. However, despite a rising number of individual studies, systematic reviews focusing specifically on these approaches in transportation research remain limited, particularly in addressing methodological challenges and data heterogeneity. This literature review addresses that gap by critically examining 81 open-access studies published between 2014 and 2024. The main challenges identified include handling linguistic diversity, integrating multimodal and geolocated data, managing short-text formats, and addressing regional and demographic bias. In response, this review proposes a methodological framework for study selection and bibliometric analysis, classifies the most commonly applied machine learning models for sentiment and topic extraction, and synthesizes findings regarding data sources, model performance, and application contexts in transportation. Additionally, it discusses unresolved gaps and ethical concerns related to representativeness and social media governance. This review highlights the transformative potential of combining sentiment analysis and topic modeling to support smarter, more inclusive, and sustainable transportation policies by offering an integrative and critical perspective. Full article

Understanding user interaction patterns during technology-triggered public discourse provides critical insights into how emerging technologies gain social meaning. This study develops an intelligent digital twin framework for modeling discourse dynamics around DeepSeek, an indigenous large language model that generated approximately 250,000 social media interactions during a 13-day period. By integrating LLM-enhanced semantic analysis with agent-based modeling, we create a comprehensive virtual representation that captures both content characteristics and behavioral dynamics. Our analysis identifies six distinct thematic domains that structure public engagement: Technological Competition, Technological Breakthrough, User Feedback, Financial Market, Social Influence, and Information Security. The agent-based simulation reveals distinctive participation and sentiment patterns across different user segments, with general users expressing stronger positive sentiments than domain experts and institutional accounts. Network analysis demonstrates the evolution from random-like initial connection patterns to scale-free structures with pronounced influence hubs. The simulation results illuminate how individual behaviors aggregate to produce complex discourse patterns, offering insights into the micro-mechanisms underlying technology reception. This research advances digital twin methodologies beyond physical systems into social phenomena, providing a framework for anticipating public responses to technological innovations and informing more effective communication strategies. Full article