Social Network Information Research Articles

Status Fulfillment through Social Networks: Impact of Hierarchies on Social Differentiation and Well-being

This study examines the multifaceted impacts of hierarchical systems and social networking on social differentiation, network formation, and individual well-being. Employing a comprehensive literature review and meta-analysis, it explores the dynamics of power and status within organizations, the influence of social resources on socioeconomic status, and the role of social networking sites in shaping social capital and psychological health. The research investigates how hierarchical structures within organizations and informal social settings contribute to social differentiation, examining the effects of power, status, and social resources on individual and group dynamics. Additionally, it assesses the impact of social networking sites on social well-being, career development, and psychological health, considering both the positive and negative consequences of online social interactions. The study reveals that while hierarchical systems and social networking can foster social capital, professional growth, and enhanced well-being, they also pose risks of social inequality, psychological distress, and exacerbated mental health issues. The findings underscore the complexity of social relations in the digital age, offering insights for developing more inclusive social structures and healthier digital interaction spaces. This research contributes to a deeper understanding of the interplay between social hierarchies, networking, and well-being, providing valuable implications for organizational leaders, policymakers, and individuals navigating social differentiation and digital socialization.

Cross-domain information fusion and personalized recommendation in artificial intelligence recommendation system based on mathematical matrix decomposition

Given the challenges of inter-domain information fusion and data sparsity in collaborative filtering algorithms, this paper proposes a cross-domain information fusion matrix decomposition algorithm to enhance the accuracy of personalized recommendations in artificial intelligence recommendation systems. The study begins by collecting Douban movie rating data and social network information. To ensure data integrity, Levenshtein distance detection is employed to remove duplicate scores, while natural language processing technology is utilized to extract keywords and topic information from social texts. Additionally, graph convolutional networks are utilized to convert user relationships into feature vectors, and a unique thermal coding method is used to convert discrete user and movie information into binary matrices. To prevent overfitting, the Ridge regularization method is introduced to gradually optimize potential feature vectors. Weighted average and feature connection techniques are then applied to integrate features from different fields. Moreover, the paper combines the item-based collaborative filtering algorithm with merged user characteristics to generate personalized recommendation lists.In the experimental stage, the paper conducts cross-domain information fusion optimization on four mainstream mathematical matrix decomposition algorithms: alternating least squares method, non-negative matrix decomposition, singular value decomposition, and latent factor model (LFM). It compares these algorithms with the non-fused approach. The results indicate a significant improvement in score accuracy, with mean absolute error and root mean squared error reduced by 12.8% and 13.2% respectively across the four algorithms. Additionally, when k = 10, the average F1 score reaches 0.97, and the ranking accuracy coverage of the LFM algorithm increases by 54.2%. Overall, the mathematical matrix decomposition algorithm combined with cross-domain information fusion demonstrates clear advantages in accuracy, prediction performance, recommendation diversity, and ranking quality, and improves the accuracy and diversity of the recommendation system. By effectively addressing collaborative filtering challenges through the integration of diverse techniques, it significantly surpasses traditional models in recommendation accuracy and variety.

Cancer Survivors’ and Care Partners’ Audio Diaries on Stress and Social Support Resources During the COVID-19 Pandemic

ObjectivesTo describe cancer survivors’ and care partners’ perceived stress and social support during the COVID-19 pandemic and assess the feasibility of audio diaries for assessing role-related needs and resources. MethodsParticipants (N = 51; n = 28 survivors, n = 23 care partners) recorded three monthly audio diaries reporting stress and support experiences. Diaries were transcribed and content-analyzed using a hybrid approach. Stress-related content was inductively coded, and social support content was deductively coded by type (instrumental, information, emotional, companionship, appraisal; κ = 0.75) then inductively coded. Descriptive statistics summarized sociodemographic data and compared coding frequencies by role. We developed narrative summaries of stress and support categories and selected quotes for contextual detail. ResultsCancer-related stressors were most prevalent (28.8%), followed by work (26.8%), family (23.1%), social isolation (13.4%), and finances (8.0%). While no significant difference in reporting frequency was observed between roles, cancer-related stress was more prevalent for survivors while work-related stress was mentioned more by care partners. Emotional support was the most prevalent support type (32.1%), followed by companionship (25.3%), appraisal (17.9%), instrumental (16.67%), and informational support (8%). Survivors reported more appraisal support than care partners (χ2 = 6.48, df = 1, P = .011) and more support for self-care, while care partners expressed more other-oriented concerns and focused more on managing responsibilities and interactions outside the household. ConclusionsThe pandemic complicated and intensified role-based stressors already present in the survivorship context. Our findings highlight the importance of informal social support networks, particularly when access to formal services is limited, and suggest that audio diaries can be an effective tool for assessing support needs and resources. Implications for Nursing PracticeNurses and healthcare providers should tailor social support assessments to address the distinct support needs and individual resources of cancer survivors and their care partners. This is especially critical in contexts that limit access to care and formal services.

Enhancing Multi-Scale Diffusion Prediction via Sequential Hypergraphs and Adversarial Learning

Information diffusion prediction plays a crucial role in understanding the propagation of information in social networks, encompassing both macroscopic and microscopic prediction tasks. Macroscopic prediction estimates the overall impact of information diffusion, while microscopic prediction focuses on identifying the next user to be influenced. While prior research often concentrates on one of these aspects, a few tackle both concurrently. These two tasks provide complementary insights into the diffusion process at different levels, revealing common traits and unique attributes. The exploration of leveraging common features across these tasks to enhance information prediction remains an underexplored avenue. In this paper, we propose an intuitive and effective model that addresses both macroscopic and microscopic prediction tasks. Our approach considers the interactions and dynamics among cascades at the macro level and incorporates the social homophily of users in social networks at the micro level. Additionally, we introduce adversarial training and orthogonality constraints to ensure the integrity of shared features. Experimental results on four datasets demonstrate that our model significantly outperforms state-of-the-art methods.

Robust social recommendation based on contrastive learning and dual-stage graph neural network

GNN-based social recommendation aims to use social network information to improve recommendation performance of traditional user–item interaction network (U–I network). However, in graph neural network information aggregation, both social networks and U–I networks inevitably have noise, which affects accuracy of recommendation results. To reduce the noise impact of network data, we propose Robust Social Recommendation based on Contrastive Learning and Dual-Stage Graph Neural Network (CLDS). First, considering instability of social networks, we propose the social preference network. It is robust and retains only social friend relationships with common preferences. Based on it and U–I network, we construct a social recommendation pre-training model. Next, we propose self-contrastive learning method. The method initializes multiple social network node representations through Gaussian distribution, pre-training and random disturbance, respectively. Then, it uses contrastive learning on the generated multiple node representations to enhance the robustness of node representation. Finally, CLDS avoids directly capturing potentially user–user and item–item information in U–I networks which is incomplete and untrusted. And instead, it only extracts user–item information to reduce the noise generated by GNN-based U–I network information aggregation. We conduct experiments under the open-source real network dataset. The experimental results show that CLDS outperforms state-of-art methods in social recommendation. The code is available at: https://github.com/Andrewsama/CLDS-master.

Graph-aware multi-feature interacting network for explainable rumor detection on social network

At present, rumors are growing wantonly with the convenience and influence of social media, becoming a problem that may severely impact social stability and development. The rumor is not an objective judgment but a process of multi-dimensional subjective value superposition and a collective transaction of people’s thoughts on social networks. How to fully mine the critical features of rumor detection from the complex information of social networks is a challenge to the existing rumor detection models. Therefore, we present the explainable model GMIN (Graph-aware Multi-feature Interacting Network), aiming to fully exploit the multifaceted features of social networks by deeply analyzing the mechanism of rumor propagation and the nature of social networks. GMIN incorporates four modules to capture: the characteristics of people receiving and spreading information, the interactions and latent associations in social networks, the mechanisms of rumor propagation and diffusion, and the collaborations between various features. It is worth noting that GMIN is interpretable in the results and the model’s components. The experimental results on three real-world datasets demonstrate the validity of our proposed model and show excellent capabilities in early rumor detection and the interpretability of the model.

Estimating the Expected Influence Capacities of Nodes in Complex Networks under the Susceptible-Infectious-Recovered Model

In recent years, epidemic modeling in complex networks has found many applications, including modeling of information or gossip spread in online social networks, modeling of malware spread in communication networks, and the most recent model of the COVID-19 pandemic. If the information disseminated is accurate, for example, maximizing its distribution is desirable, whereas if it is a rumor or a virus, its spread should be minimized. In this context, it is very important to identify super-spreaders that maximize or minimize propagation. Lately, studies for detecting super-spreaders have gained momentum. Most of the studies carried out aim to distinguish the influences of nodes under a specific propagation model (such as SIR) using network centrality measures and subsequently, to rank the nodes accordingly. However, in this study, we developed an algorithm that approximates the expected influence of nodes under the popular SIR model. By considering the behavior of the SIR model and only the shortest paths between nodes, the algorithm ranks the nodes according to this approximated value. Our developed algorithm is named the Expected Value Estimation (EVE). We compared the performance of EVE, using different SIR settings on real-world datasets, with that of many current well-known centrality measures. The experimental studies demonstrated that the solution quality (ranking capability) of EVE is superior to that of its competitors.

Features of the formation of healthcare competence of higher education acquires

The article reveals the peculiarities of the formation of health-saving competence of higher education students in the process of physical education. A theoretical analysis of the literature sources of the studied phenomenon is carried out and it is determined that the preservation and promotion of student health is the most necessary task in higher education institutions. It is emphasized that the peculiarities of the living conditions of modern youth, environmental problems, the growth of harmful information in social networks, the continuous development of technological progress, the abuse of bad habits as opposed to a healthy lifestyle, limited physical activity and other factors negatively affect the health of modern student youth. It is noted that higher education institutions should pay more attention to the introduction of innovative content, forms, methods and technologies aimed at forming the health-saving competence of students during physical education classes.
 It was made conclusions that in the formation of health-saving competence of students in the process of physical education, teachers should should try to solve such problems as: forming an understanding of the importance of health competence; promoting the improvement of higher education students' levels of physical and mental fitness; use of innovative means of teaching and education innovative means of teaching and upbringing; monitoring and evaluation of the results of students' educational activities by means of physical education; coverage of more students who do not have the opportunity to attend physical education classes; organization of distance learning and training for higher education students; popularization and promotion of a healthy lifestyle through the use of modern digital technologies; creating opportunities for students to be involved in physical education and recreation activities (to improve physical health).

Deep neural networks for corporate misconduct prediction in construction industry using data from social networks

Given the complex and continually adapting nature of misconduct, this study aims to update and interpret a misconduct prediction model using the latest techniques, i.e., deep neural networks (DNN) and social network information for Chinese construction companies. Social networks have been reported as drivers of corruption in the construction industry; however, such networks are seldom included as inputs in existing models. Based on data from 119 listed Chinese construction firms, this study applied a DNN to construct a corporate misconduct prediction model. The inputs of this model included variables related to corporate governance and financial performance, as examined in previous studies, but also social network information. This study found that the DNN demonstrated superior performance compared to benchmark models. To interpret the constructed model further and assess the role of social networks in predictions, this study also employed SHapley Additive exPlanations (SHAP), which could calculate the importance of each variable. The 20 most influential variables were identified, almost 50% of which were related to social networks. The findings indicate that the proposed model can be applied to guide shareholders and regulators in taking actions to detect and prevent corporate misconduct and aid investors in making appropriate investment decisions.

Domain adaptive learning based on equilibrium distribution and dynamic subspace approximation

Nowadays, big data analysis has become an important approach in social information network. However, the social information may not be distributed independently and identically (i.i.d.), which can be addressed using domain adaptation. However, most of the existing domain adaptation methods are designed to align cross-domain distributions. The label information of the samples in the target domain is completely unavailable. Thus, the class-conditional distribution differences cannot be well measured, and the effect of feature distortion on distribution alignment in the original feature space is difficult to handle. This paper proposes a domain adaptation learning based on the Equilibrium Distribution and Dynamic Subspace Approximation (EDDSA) to alleviate these problems. First, EDDSA learns to project the source and target domains into associated feature spaces, and dynamically approximates two subspaces to overcome the feature distortion problem. Second, the balanced distribution alignment term is introduced to dynamically weight the importance of the conditional and marginal distributions. Through many experiments, EDDSA is superior to most traditional methods.

Sites and Ways of Belonging to Diaspora Networks: The Case of the Greek Second Generation in Italy

Abstract To survive over time, a diaspora must create sites of belonging and micro places in which to concentrate the main elements of its “iconography” that can consolidate social networks. This article analyzes how second-generation Greeks in Italy fit into diaspora networks by investigating the ways in which they define their sense of Greekness and use their ethnic resources. The findings of field research show a weakness of (formal and informal) social network ties and the pre-eminence of the family’s role in the process of sociocultural identification and ethnic identity construction. In fact, the second generation’s “ways of belonging” and the sense of attachment to Greece have an autonomous significance and are expressed more at a familial level and less collectively. Familial socialization plays a mediating role in the process of identification and transmission of Greekness, as well as in guiding ways of employing ethnic resources, contributing to the maintenance of the diaspora.

Seeking information and services associated with reproductive health among rural Peruvian young adults: exploratory qualitative research from Amazonas, Peru.

Sexual and reproductive health (SRH) literacy allows young adults to make informed decisions about health outcomes. In Peru, roughly one fifth of the population lives in rural areas, and little is known about where young adults in rural areas get their SRH information. The aim of this study was to identify what motivates and influences young adults to seek information and care related to SRH in three rural communities in the highlands of Northern Peru. Five gender-stratified focus group discussions with a total of 24 participants, and nine follow-up interviews were conducted to generate in-depth narrative data and triangulate data from the target group. Participants were women and men aged 18-24. The focus group discussions and interviews explored sources of reproductive health information, the role of informal social networks, barriers to care, and primary health concerns of the target population. Main findings include: (1) The two greatest perceived SRH risks were unwanted pregnancy and abnormal discharge; (2) There appears to be limited concern about HIV or other sexually transmitted infections in the narratives; (3) There is a low quality of information concerning SRH, with discrepancies between the genders; (4) A broad spectrum of sources for SRH information were cited, including Internet, traditional healers, and specialized care; and varied by gender and life experience; (5) Having trust in the information source was the primary variable associated with uptake of services and/or access to information for both men and women. However, men reported more embarrassment around seeking services and information, whereas women faced more physical barriers. There is a lack of SRH information among young adults in some communities in the northern highlands of Peru. Both schools and health centers were noted as being trusted and established information sources for all genders so could be a key resource to explore as a way to disseminate information.

UNVERIFIED INFORMATION IN SOCIAL NETWORKS: ANALYSIS FROM AN ISLAMIC PERSPECTIVE

In contemporary society, social media has evolved into an indispensable and pervasive tool, impacting individuals worldwide across various dimensions, including the personal, social, economic, and political spheres. The basic expectation from social networks is to serve the people and society by providing important, authentic information and verified news. Unfortunately, false news, rumours and fabricated information on social networks have become a threat to individuals, and a destructive tool for peace and societal harmony. The unregulated proliferation of hoaxes on social networks can lead to a myriad of societal disruptions and issues, thereby intensifying the need for harmonious and peaceful coexistence as advocated by both individuals and society at large. This is a qualitative descriptive article that explores the Islamic understanding and rulings on the spread of unverified information in social networks intentionally for gaining personal interest or political advantages. The article also recommends some ethical and moral precepts of revealed knowledge to ensure the proper use of social networks for the benefit of individuals and community, and to avoid unethical violation and immoral actions.

C-privacy: a social relationship-driven image customization sharing method in cyber-physical networks

Cyber-Physical Networks(CPN) are comprehensive systems that integrate information and physical domains, and are widely used in various fields such as online social networking, smart grids, and the Internet of Vehicles(IoV). With the increasing popularity of digital photography and Internet technology, more and more users are sharing images on CPN. However, many images are shared without any privacy processing, exposing hidden privacy risks and making sensitive content easily accessible to Artificial Intelligence(AI) algorithms. Existing image sharing methods lack fine-grained image sharing policies and cannot protect user privacy. To address this issue, we propose a social relationship-driven privacy customization protection model for publishers and co-photographers. We construct a heterogeneous social information network centered on social relationships, introduce a user intimacy evaluation method with time decay, and evaluate privacy levels considering user interest similarity. To protect user privacy while maintaining image appreciation, we design a lightweight face-swapping algorithm based on Generative Adversarial Network(GAN) to swap faces that need to be protected. Our proposed method minimizes the loss of image utility while satisfying privacy requirements, as shown by extensive theoretical and simulation analyses.

Informal Caregiver Social Network Types and Mental Health: The Mediating Role of Psychological Resilience

ABSTRACT Little is known about whether and why social networks protect mental health among informal caregivers. This study examined the association between informal caregiver social network types and depressive symptoms and the mediatory mechanism of psychological resilience. Latent class analysis, applied to cross-sectional data on 278 Singaporean caregivers, identified four social network types: restricted (42%), friend (16%), family (21%), and diverse (21%). Path analysis showed that the diverse social network type, compared to the restricted social network type, was associated with a lower level of depressive symptoms, and psychological resilience fully mediated this association. Interventions should help caregivers to maintain social networks with their family and friends.

Perceived social support and characteristics of social networks of families with children with special healthcare needs following the COVID-19 pandemic.

Children with special healthcare needs (CSHCN) require more support than the average of their peers. Support systems for CSHCN were particularly affected by pandemic control measures. Perceived social support is a resource for health and wellbeing for CSHCN and their families. Associations of social support, mental health and socioeconomic status (SES) have been described. This study aims to (1) assess perceived social support in families with and without CSHCN; (2) describe structure and types of social networks of families with and without CSHCN; and (3) explore associations between perceived social support, disease complexity, child and caregiver mental health, and SES. This is the third of a sequential series of cross-sectional online surveys conducted among caregivers of children ≤ 18 years in Germany since the beginning of the COVID-19 pandemic, administered between 1st December 2022 and 10 March 2023. The Brief Social Support Scale (BS6) assessed perceived social support. Child and parental mental health were assessed using the Strengths and Difficulties Questionnaire (SDQ) and WHO-5 Wellbeing index. The CSHCN-Screener identified CSHCN. Descriptive statistics and linear regression modeling assessed associations between perceived social support, parent-reported child mental health problems, disease complexity, caregiver mental wellbeing and SES. The final sample included 381 participants, among them 76.6% (n = 292) CSHCN. 46.2% (n = 176) of caregivers reported moderate, i.e., at least occasional social support. Social support was largely provided by informal social networks consisting of partners, relatives and neighbors/friends. Linear regression modeling revealed associations of lower perceived social support with higher disease complexity of the child, lower caregiver mental wellbeing, lower SES and increasing caregiver age. The results of this study describe inequalities in perceived social support according to disease complexity of the child, caregiver mental health and socioeconomic status. They highlight the importance of social support and support networks as a resource for wellbeing of caregivers and CSHCN. Moving on from the COVID-19 pandemic, recovery strategies should focus on low-threshold interventions based in the community to improve social support for families with CSHCN and actively involve caregivers in identifying needs and co-creating new approaches.

The ontogeny of social networks in wild great tits (Parus major).

Sociality impacts many biological processes and can be tightly linked to an individual's fitness. To maximize the advantages of group living, many social animals prefer to associate with individuals that provide the most benefits, such as kin, familiar individuals, or those of similar phenotypes. Such social strategies are not necessarily stable over time but can vary with changing selection pressures. In particular, young individuals transitioning to independence should continuously adjust their social behavior in light of developmental changes. However, social strategies exhibited during adolescence in animals are understudied, and the factors underlying social network formation during ontogeny remain elusive. Here, we tracked associations of wild great tits (Parus major) during the transition to independence and across their first year of life. Both spatial and social factors predicted dyadic associations. During the transition to independence in spring, fledglings initially preferred to associate with siblings and peers over non-parent adults. We found no evidence for preferred associations among juveniles of similar age or fledge weight during that time but weak evidence for some potential inheritance of the parental social network. By autumn, after juveniles had reached full independence, they exhibited social strategies similar to those of adults by establishing stable social ties based on familiarity that persisted through winter into the next spring. Overall, this research demonstrates dynamic changes in social networks during ontogeny in a species with a fast life history and limited parental care, which likely reflect changes in selective pressures. It further highlights the importance of long-term social bonds based on familiarity in this species.

Social networks and dispositional factors determining housing status of urban residents: evidence from Ethiopia

This article examines the social networks and dispositional factors that affect the housing status of urban residents. Despite their considerable role in the housing market, this paper stresses the limited attention these factors have received in housing studies. The study collected data from a sample of individuals in Sebeta, Ethiopia, and their impact on housing status was studied using various statistical and econometric methods. This study utilized empirical analysis to examine multiple social network factors, such as political affiliation, informal social networks, parental support, and past experiences in brokerage. The results highlighted the critical role that social and dispositional elements play in shaping housing status outcomes. Disparities in housing status were observed between individuals with and without social networks, and these differences were attributed to dispositional factors. The findings suggest that future housing development initiatives must account for individuals’ social and dispositional differences. Further research can build upon these findings to inform future housing policies that address these disparities.

Social Experiences and Health Needs of Patients with Severe Mental Illness and their Caregivers during the first year of the COVID-19 pandemic in Spain

Background The strict isolation measures for the population imposed by the health authorities caused a prolonged disruption of informal social support networks. Both this new social situation and the decrease in accessibility to health care have generated new needs in people with severe mental illness (SMI) and their caregivers. Objectives This study provides insight into life experiences and health needs of a population with SMI during the first year of the COVID-19 pandemic in Spain. Methods Qualitative design using semi-structured dyadic interviews, conducted from January through December 2022. A purposive sampling of patients with SMI and their caregivers was carried out through key informants in rural and urban localities in southern Spain. Verbatims were identified and classified by triangulation after the evaluation of the interview transcripts. The codes were defined through content analysis using the NVivo software. Results Semi-structured dyadic interviews (21), identifying three main categories: 1. Social isolation: increased, causing greater personal vulnerability, exacerbation of psychiatric symptoms and exhaustion in caregivers. 2. Accessibility to Health Services : decreased with fewer face-to-face consultations, with difficulty in managing urgent situations and telephone attention in decompensated and disabled patients. 3. Continuity of healthcare: decreased with distrust in health professionals due to lack of communication between primary care and the hospital Conclusion COVID-19 confinement exacerbated loneliness and worse health self-perception in SMI people. Greater formal social support was required. GPs role is key to avoiding delays in appointments and lack of coordination between primary and specialised care.

Fair division with minimal withheld information in social networks

We present a study of a few graph-based problems motivated by fair allocation of resources in a social network. The central role in the paper is played by the following problem: What is the largest number of items we can allocate to the agents in the given social network so that each agent hides at most one item and overall at most k items are hidden, and no one envies its neighbors? We show that the problem admits an XP algorithm and is W[1]-hard parameterized by k. Moreover, within the running time, we can identify agents that should hide its items and can construct an ordering in which agents should pick items into its bundles to get a desired allocation. Besides this problem, we also consider the existence and verification versions of this problem. In the existence problem, we are given a social network, valuations, a budget, and the goal is to find an allocation without envy. In the verification problem, we are additionally given an allocation, and the goal is to determine if the allocation satisfies the required property.