Noreen Fuentes¹, Janeth Ugang¹, Narcisan Galamiton¹, Suzette Bacus¹, Samantha Shane Evangelista², Fatima Maturan², Lanndon Ocampo^2,3,*

CMC-Computers, Materials & Continua, Vol.86, No.1, pp. 1-26, 2026, DOI:10.32604/cmc.2025.068104 - 10 November 2025

Abstract This study demonstrates a novel integration of large language models, machine learning, and multi-criteria decision-making to investigate self-moderation in small online communities, a topic under-explored compared to user behavior and platform-driven moderation on social media. The proposed methodological framework (1) utilizes large language models for social media post analysis and categorization, (2) employs k-means clustering for content characterization, and (3) incorporates the TODIM (Tomada de Decisão Interativa Multicritério) method to determine moderation strategies based on expert judgments. In general, the fully integrated framework leverages the strengths of these intelligent systems in a more systematic evaluation… More >

Luyu Ma^1,*, Xiu Cheng^1,*, Zongyan Xing¹, Yue Wu¹, Weiwei Jiang²

CMC-Computers, Materials & Continua, Vol.85, No.2, pp. 3921-3943, 2025, DOI:10.32604/cmc.2025.067786 - 23 September 2025

Abstract Green consumption (GC) are crucial for achieving the Sustainable Development Goals (SDGs). However, few studies have explored public attitudes toward GC using social media data, missing potential public concerns captured through big data. To address this gap, this study collects and analyzes public attention toward GC using web crawler technology. Based on the data from Sina Weibo, we applied RoBERTa, an advanced NLP model based on transformer architecture, to conduct fine-grained sentiment analysis of the public’s attention, attitudes and hot topics on GC, demonstrating the potential of deep learning methods in capturing dynamic and contextual… More >

Alican Kaya¹, Emre Seyrek², Abdulselami Sarıgül³, Mehmet Şata⁴, Juan Gómez-Salgado^5,6,*, Murat Yıldırım^7,8,*

International Journal of Mental Health Promotion, Vol.27, No.8, pp. 1149-1163, 2025, DOI:10.32604/ijmhp.2025.067388 - 29 August 2025

Abstract Background: Social media addiction, one of the behavioural addictions, is a significant predictor of job performance. It has also been posited that individuals whose fundamental requirements (e.g., sleep) are not sufficiently met and who lack adequate support (e.g., perceived social support) are incapable of effectively harnessing their potential. The primary objective of this study is to examine the mediating effects of sleep disorder and perceived social support on the relationship between social media addiction and job performance. Furthermore, it seeks to explore the moderating effects of perceived social support on sleep disorders and job performance.… More >

Kexuan Niu, Xiameng Si^*, Xiaojie Qi, Haiyan Kang

CMC-Computers, Materials & Continua, Vol.85, No.1, pp. 2051-2070, 2025, DOI:10.32604/cmc.2025.065377 - 29 August 2025

Abstract Sarcasm detection is a complex and challenging task, particularly in the context of Chinese social media, where it exhibits strong contextual dependencies and cultural specificity. To address the limitations of existing methods in capturing the implicit semantics and contextual associations in sarcastic expressions, this paper proposes an event-aware model for Chinese sarcasm detection, leveraging a multi-head attention (MHA) mechanism and contrastive learning (CL) strategies. The proposed model employs a dual-path Bidirectional Encoder Representations from Transformers (BERT) encoder to process comment text and event context separately and integrates an MHA mechanism to facilitate deep interactions between More >

Lihua Zuo^1,2,#, Jian Mao^2,#,*

Journal of Psychology in Africa, Vol.35, No.2, pp. 241-247, 2025, DOI:10.32604/jpa.2025.065765 - 30 June 2025

Abstract This study examined how social desirability responses confound the relationship between gender and social media addiction. A total of 496 college student social media users (females = 310, 62.5%, mean age = 20.15, SD = 1.26) completed an online questionnaire on Social Media Addiction and Social Desirability. Mediation analysis revealed that females were at higher risk for social media addiction. On the other hand, the indirect effect of gender on social media addiction via social desirability is associated with lower social media addiction, which suggests that social desirability had a suppression effect on social media More >

Suliman Mohamed Fati^1,*, Mohammed A. Mahdi², Mohamed A.G. Hazber², Shahanawaj Ahamad³, Sawsan A. Saad⁴, Mohammed Gamal Ragab⁵, Mohammed Al-Shalabi²

CMES-Computer Modeling in Engineering & Sciences, Vol.143, No.2, pp. 2109-2131, 2025, DOI:10.32604/cmes.2025.063092 - 30 May 2025

Abstract Cyberbullying on social media poses significant psychological risks, yet most detection systems oversimplify the task by focusing on binary classification, ignoring nuanced categories like passive-aggressive remarks or indirect slurs. To address this gap, we propose a hybrid framework combining Term Frequency-Inverse Document Frequency (TF-IDF), word-to-vector (Word2Vec), and Bidirectional Encoder Representations from Transformers (BERT) based models for multi-class cyberbullying detection. Our approach integrates TF-IDF for lexical specificity and Word2Vec for semantic relationships, fused with BERT’s contextual embeddings to capture syntactic and semantic complexities. We evaluate the framework on a publicly available dataset of 47,000 annotated social… More >

Ananya Jha¹, Amaresh Jha^2,*

Journal of Cyber Security, Vol.7, pp. 109-134, 2025, DOI:10.32604/jcs.2025.064429 - 30 May 2025

Abstract This paper explores the methodologies employed in the study of mobile and social media phishing, aiming to enhance the understanding of these evolving threats and develop robust countermeasures. By synthesizing existing research, we identify key approaches, including surveys, controlled experiments, data mining, and machine learning, to gather and analyze data on phishing tactics. These methods enable us to uncover patterns in attacker behavior, pinpoint vulnerabilities in mobile and social platforms, and evaluate the effectiveness of current detection and prevention strategies. Our findings highlight the growing sophistication of phishing techniques, such as social engineering and deceptive More >

Kagiso Komane^1,*, Lucas Khoza², Fani Radebe¹

Journal of Cyber Security, Vol.7, pp. 79-108, 2025, DOI:10.32604/jcs.2025.059712 - 20 May 2025

Abstract Financial support, government support, cyber hygiene, and ongoing education and training as well as parental guidance and supervision are all essential components of cybersecurity awareness (CSA) identified in this study among the youth. It’s critical to realize that adequate funding is needed to effectively increase CSA, particularly among South African youth. Previous studies have demonstrated several ways to address inadequate CSA by utilizing various cybersecurity frameworks, ideas, and models. To increase CSA, this literature review seeks to emphasize the significance of integrating cybersecurity education throughout the entire school curriculum. This paper identified ethical issues, protection… More >

Xiang Shi^1,2,3, Ju Feng^1,2,3, Ming Gong^1,2,3, Yingxiu Chen^1,2,3, Jianyong Chen^1,2,3,*

Journal of Psychology in Africa, Vol.35, No.1, pp. 143-150, 2025, DOI:10.32604/jpa.2025.065772 - 30 April 2025

Abstract While the relation between shyness and problematic social media use (PSMU) among adolescents has been established, the mediating and moderating mechanisms underlying this association remain largely unexplored. The present study examined whether psychological insecurity mediated the association between shyness and adolescents’ PSMU and whether this mediation was moderated by relational-interdependent self-construal (RISC). A total of 1506 Chinese adolescents (M_age = 13.74 years, SD = 0.98) filled out self-report measures of shyness, psychological insecurity, RISC, and PSMU. SPSS (version 23.0) and the PROCESS macro (version 4.1) were employed to test the proposed model. Mediation analyses indicated that… More >

Haohan Zhao¹, Xingchen Zhu², Wencan Li^3,*, Xin Lin^4,*

International Journal of Mental Health Promotion, Vol.27, No.4, pp. 517-540, 2025, DOI:10.32604/ijmhp.2025.062739 - 30 April 2025

Abstract Background: Despite increasing attention to parental educational anxiety in China’s educational system, the underlying mechanisms through which this anxiety affects adolescent academic performance remain unclear. This study aims to investigate how parental educational anxiety influences academic outcomes through depression and self-efficacy while considering the role of problematic social media use in today’s digital age. Methods: Data analysis was conducted using stratified random cluster sampling techniques. Participants for this study were recruited from middle and high schools in China. The sample comprised 2579 traditional two-parent families, each consisting of a pair of parents and one child.… More >