Social Network Data Research Articles

How Clinician-Scientists Access and Mobilise Social Capital and Thus Contribute to the Professional Development of Their Colleagues in Their Networks

ABSTRACT Clinician-scientists, physicians who conduct research, may fulfil a bridging role in networks of health care researchers and practitioners. Within clinician-scientists’ networks, knowledge sharing is thought to play a vital role in the continuing professional development of themselves and their colleagues. However, little is known about networks of clinician-scientists and how this impacts continuing professional development. Rooted in social capital theory, this study provides a mixed methods exploration of clinician-scientists’ networks. Ego-level social network data were collected via semi-structured interviews on professional interactions about evidence-based practice with 15 clinician-scientists in the area of general practice and elderly care. Quantitative analysis revealed that professional networks of clinician-scientists varied in size, composition, and frequency of interactions depending on appointed research time and experience. Less experienced clinician-scientists interacted most frequently with other clinician-scientists while experienced clinician-scientist experienced more sporadically with clinicians. Clinician-scientists with more research time interacted more frequently with scientists and had a slightly larger professional network than those with less research time. The thematic qualitative analysis revealed different decision-making processes of clinician-scientists on mobilising their social capital and connecting to others in the network: (1) deliberate decision about initiating connections; (2) reactive behaviour without a decision; (3) ad-hoc decision. Clinician-scientists exchange knowledge to enhance their own continuing professional development mainly but also contribute to the professional development of clinicians, scientists, and other clinician-scientists.

IBCFaiCDR: Auxiliary data-driven item-based collaborative filtering in cross-domain RSs to address user cold start problem

The adoption of Recommender Systems (RSs) in various services is imperative in the present era. One of the inherent challenge faced by RSs is the user cold start problem (UCS) and it occurs when there is a lack of enough data available for a new user, which restricts the capacity to provide accurate recommendations. Researchers have conducted investigations into the utilization of auxiliary data like social network data, review text, demographic information etc., to augment the RSs ability to learn and understand the user's preferences, with the aim of solving this issue. The provided information is inadequate due to the restricted level of user engagement within the specified domain. The researchers utilize a Cross-Domain RS (CDR) that incorporates information from multiple domains to provide personalized suggestions to users. Item Based Collaborative Filtering (IBCF), which utilizes item-item similarity, is commonly used when dealing with sparse data. The suggested collaborative filtering technique employs IBCF which uses the item similarity obtained with item features. These features are generated by the proposed approach IBCFaiCDR's model, trained on source domain data such as product images and reviews. The efficacy of the proposed approach is assessed using a large dataset from Amazon, consisting of user interactions across many categories. The results on target domain, evaluated using MAE and RMSE, indicate that the inclusion of auxiliary information (image + text) enhances the RS performance for new users.

Linked Employer–Employee Data from XING and the Mannheim Enterprise Panel

Abstract The availability of social media data is growing and represents a new data source for economic research. This paper presents a detailed study on the use of data from a career-oriented social networking platform. The employment data are exported from user profiles and linked to the Mannheim Enterprise Panel (MUP). The linked employer–employee (LEE) data consist of 14 million employments for 1.5 million employers and describes around 9 million employee flows. Plausibility checks confirm that career-oriented social networking data contain valuable information about employments and employee flows. Using such platform data provides opportunities for research on employee mobility, networks, and local ecosystems’ role in economic performance at the employer and the regional level.

Adaptive Strategies and Sustainable Innovations of Chinese Contractors in the Belt and Road Initiative: A Social Network and Supply Chain Integration Perspective

As global economic integration and rapid technological advancements transform international business, international engineering contracting has become essential for achieving sustainable development goals (SDGs). This paper investigates the significant impact of China’s strategic initiatives, notably the “Going Global” strategy and the Belt and Road Initiative (BRI), on the operational practices of Chinese enterprises involved in overseas investments. Central to this transformation is the Engineering, Procurement, and Construction (EPC) model, which emphasizes the integration of supply chain management and stakeholder collaboration to enhance performance in international EPC projects and underscores the crucial role of these elements in promoting sustainability. Incorporating insights from social network data analysis, this study reveals that contractors collaborating with various stakeholders—such as owners/consulting engineers, domestic and foreign customs departments, and group headquarters/design parties—exhibit a high degree of similarity in personnel profiles. This suggests that the internal organizational structure and personnel allocation of contractors could be optimized to enhance operational efficiency, aligning with the collaborative patterns identified. This study addresses a critical research gap by exploring how effective supply chain management and collaborative stakeholder engagement within multinational EPC projects contribute to sustainable outcomes. Employing advanced social network analysis software, the research examines the complex interactions among stakeholders and their influence on procurement dynamics. Findings indicate that strong relational networks and strategic collaborations significantly enhance procurement efficiency and project success, underscoring the importance of supply chain integration. Ultimately, integrating supply chain management principles into the EPC model not only offers innovative perspectives for advancing sustainability in international projects but also provides actionable insights for improving project outcomes within the BRI framework. This research underscores the pivotal role of supply chain organization and stakeholder cooperation in achieving sustainability objectives, thereby enriching the discourse on sustainable enterprise operation and supply chain management in the context of global initiatives.

Working in a relational way is everything: Perceptions of power and value in a drug policy-making network

BackgroundThe development of drug policies has been a major focus for policy-makers across North America in light of the ongoing public health emergency caused by the overdose crisis. In this context, the current study examined stakeholders’ experiences and perceptions of power and value in a drug policy-making process in a North American city using qualitative, questionnaire, and social network data.MethodsWe interviewed 18 people who participated in the development of a drug policy proposal between October 2021 and March 2022. They represented different groups and organizations, including government (n = 3), people who use drugs-led advocacy organizations (n = 5), other drug policy advocacy organizations (n = 5), research (n = 3) and police (n = 2). Most of them identified as men (n = 8) and white (n = 16), and their ages ranged between 30 and 80 years old (median = 50). Social network analysis questionnaires and semi-structured qualitative interviews were administered via Zoom. Social network data were analysed using igraph in R, and qualitative data were analysed using thematic analysis. The analyses explored perceptions of value and power within a drug policy-making network.ResultsThe policy-making network showed that connections could be found across participants from different groups, with government officials being the most central. Qualitative data showed that inclusion in the network and centrality did not necessarily translate into feeling powerful or valued. Many participants were dissatisfied with the process despite having structurally advantageous positions or self-reporting moderately high quantitative value scores. Participants who viewed themselves as more valued acknowledged many process shortcomings, but they also saw it as more balanced or fair than those who felt undervalued.ConclusionsWhile participation can make stakeholders and communities feel valued and empowered, our findings highlight that inclusion, position and diversity of connections in a drug policy-making network do not, in and of itself, guarantee these outcomes. Instead, policy-makers must provide transparent terms of reference guidelines and include highly skilled facilitators in policy discussions. This is particularly important in policy processes that involve historical power imbalances in the context of a pressing public health emergency.

A comparative UPLC-orbitrap-MS-based metabolite profiling of three Pelargonium species cultivated in Egypt

Several Pelargonium species are cultivated mainly to produce essential oils used in perfume industry and for ornamental purposes. Although the chemical composition and biological activities of their essential oils were extensively investigated, there is limited information about the chemical composition of their non-volatile constituents. In this study, we report an Ultra-Performance Liquid Chromatography-Mass Spectrometry (UPLC-MS)-based metabolomics approach for the annotation and analysis of various metabolites in three species; P. graveolens, P. denticulatum, and P. fragrans utilizing The Global Natural Product Social Molecular Networking (GNPS) and multivariate data analyses for clustering of the metabolites. A total of 154 metabolites belonging to different classes were annotated. The three species are good sources of coumarins, benzoic acid derivatives, organic acids, fatty acids, and phospholipids. However, the highest level of flavonols (mono- and di-O-glycosides) and cinnamic acid derivatives was found in P. graveolens and P. denticulatum, whereas tannins and flavone C-glycosides were abundant in P. fragrans. The metabolic profiles clarified here provide comprehensive information on the non-volatile constituents of the three Pelargonium species and can be employed for their authentication and possible therapeutic applications.

Hierarchical Storage for Massive Social Network Data Based on Improved Decision Tree

Hierarchical Storage for Massive Social Network Data Based on Improved Decision Tree

LEVERAGING MACHINE LEARNING FOR IMPROVED SPAM DETECTION IN ONLINE NETWORKS

This paper proposes an advanced methodology of spam detection by including N-gram tf.idf feature selection and a deep multi-layer perceptron neural network, with further improvement through the modified distribution-based balancing algorithm. Considering high-dimensional data and class imbalance problems, the proposed method proved to outperform the state-of-the-art methods on benchmark datasets, including Enron, SpamAssassin, SMS spam collection, and social networking data. It also makes up an important enhancement in the classification of spam, as it captures complex features that reduce false positives and false negatives. These results show that combining deep learning with improved feature extraction and balancing techniques provides a very robust approach for spam detection.

On the spurious effect of intergroup friendship on outgroup attitudes in schools: The role of social influence and the positive impact of exposure to outgroup peers.

Promoting intergroup friendships in schools is regarded as a powerful strategy for improving outgroup attitudes. However, stochastic actor-oriented modelling (SAOM) studies have often revealed no association between intergroup friendship and outgroup attitudes. I investigated whether SAOM studies reported no effect of intergroup friendship on outgroup attitudes, what was responsible for this surprising finding and whether exposure to outgroup peers was positively related to outgroup attitudes. The meta-analysis of SAOM studies confirms no association between intergroup friendship and outgroup attitudes. Examining longitudinal social network data of 2700 German students, I found that a positive link between intergroup friendship and outgroup attitudes appeared only when I did not control for social influence. This indicates that intergroup friendship did not automatically improve outgroup attitudes. Instead, the development of outgroup attitudes among students depended on social influence and, thus, the quality of outgroup attitudes among their outgroup friends. Exposure to outgroup peers was, however, positively associated with outgroup attitudes. These findings reframe intergroup contact theory by suggesting that intergroup friendship is not essential for improving outgroup attitudes. Rather, social influence and exposure to outgroup peers could be key factors shaping outgroup attitudes.

The credibility assessment of Twitter/X users based organization objectives by heterogeneous resources in big data life cycle

Social network data, such as Twitter/X, is of Big Social Data type. Big social data describes people's social behaviors and interactions. They have high business value for decision-making in organizations. However, because of the anonymous nature of social network users, their credibility is ambiguous. Credibility expresses the accuracy and value of big social data. Despite extensive research on the credibility of big social data, most methods have not paid sufficient attention to the important dimensions of their assessment, including user expertise based on topic, selecting social network features, and labeling them. Furthermore, these methods cannot manage the time, high volume, and speed of big social data. To address these issues, this paper presents a novel model for assessing the credibility of Twitter/X users by integrating Twitter/X with Google Scholar. The model automatically defines users' credibility labels using Google Scholar. Machine learning feature selection methods also select features that affect the credibility of Twitter/X users based on the topic. This study uses Google Scholar and the BerTopic algorithm for effective topic modeling on Twitter/X. The model considers unrelated data management, dynamic user credibility, and organizing activities based on the Big Data lifecycle. Finally, using Linear Regression, Support Vector Regression, K-Nearest Neighbor, Random Forest, Classification and Regression Trees algorithms, the model predicts the credibility of Twitter/X users and proves that it performed better than similar models through Classification and Regression Trees. In addition, the model is generalizable for all organizational purposes due to the integration of heterogeneous resources and feature selection methods.

Towards modeling and analysis of longitudinal social networks

There are various methods for handling longitudinal data in graphs and social networks, all of which have an impact on the algorithms used in data analysis. This article provides an overview of limitations, potential solutions, and unanswered questions regarding different temporal data schemas in social networks that are comparable to existing techniques. Restricting algorithms to a specific time point or layer has no effect on the results. However, when applying these approaches to a network with multiple time points, adjusted algorithms or reinterpretation becomes necessary. Therefore, using a generic definition of temporal networks as one graph, we aim to explore how we could analyze longitudinal social networks with centrality measures. Additionally, we introduce two new measures, “importance” and “change”, to identify nodes with specific behaviors. We provide case studies featuring three different real-world networks exhibiting both limitations and benefits of the novel approach. Furthermore, we present techniques to estimate variations in importance and degree centrality over time.

The Complex Mechanism of Social Networks' Influence on the Behavior of Institutional Investors

It examines the mechanism of influence on institutional investors by social networks, specifically looking at the dual roles of information dissemination and social capital accumulation. This paper collects financial data, transaction records, and social network data concerning institutional investors. Descriptive statistical analysis and multivariate regression analysis were adopted to test the critical impact of social networks on investment decisions. The results show that information sources and social capital have a significant positive impact on investment amounts. Institutional investors who can obtain direct information sources have significantly increased their investment amounts, and the accumulation of social capital also has a significant promoting effect on investment amounts. Descriptive statistical analysis reveals the differences in the social capital and information sources of different investors on their investment behaviors. Regression analysis further quantifies these effects. It can be seen that information sources and social capital were 200000 and 10000 respectively, while the P value was far less than 0.01, highly significant in general. This paper not only verifies the key role of social network in institutional investors' behavior but provides a very important reference to sponsoring actual investment decisions. It shows how social networks have a significant role in information dispersion and accumulation of social capital on the behavior of guiding institutional investors. This promotes more extensive use of the scope of social network theory applications in the context of finance literature and provides newer perspectives and strategies for institutional investors.

Spatiotemporal context transition model based on graph convolutional network and its implementation

PurposeThe purpose of this paper is to present a method that addresses the data sparsity problem in points of interest (POI) recommendation by introducing spatiotemporal context features based on location-based social network (LBSN) data. The objective is to improve the accuracy and effectiveness of POI recommendations by considering both spatial and temporal aspects.Design/methodology/approachTo achieve this, the paper introduces a model that integrates the spatiotemporal context of POI records and spatiotemporal transition learning. The model uses graph convolutional embedding to embed spatiotemporal context information into feature vectors. Additionally, a recurrent neural network is used to represent the transitions of spatiotemporal context, effectively capturing the user’s spatiotemporal context and its changing trends. The proposed method combines long-term user preferences modeling with spatiotemporal context modeling to achieve POI recommendations based on a joint representation and transition of spatiotemporal context.FindingsExperimental results demonstrate that the proposed method outperforms existing methods. By incorporating spatiotemporal context features, the approach addresses the issue of incomplete modeling of spatiotemporal context features in POI recommendations. This leads to improved recommendation accuracy and alleviation of the data sparsity problem.Practical implicationsThe research has practical implications for enhancing the recommendation systems used in various location-based applications. By incorporating spatiotemporal context, the proposed method can provide more relevant and personalized recommendations, improving the user experience and satisfaction.Originality/valueThe paper’s contribution lies in the incorporation of spatiotemporal context features into POI records, considering the joint representation and transition of spatiotemporal context. This novel approach fills the gap left by existing methods that typically separate spatial and temporal modeling. The research provides valuable insights into improving the effectiveness of POI recommendation systems by leveraging spatiotemporal information.

The Ties That Bind: The Association Between Social Network Ties, Integration, and Stress Among Incarcerated Women

Social integration is theorized to enhance psychological well-being and reduce stress among incarcerated women. However, little empirical research has examined the association between prison social integration and women’s stress during incarceration. This study expands on previous research by (a) examining the relationship between different types of prison network ties among incarcerated women and self-reported stress and (b) exploring whether women’s perceptions of social integration mediate the association between prison network ties and stress. Using ordinal logistic models that incorporate social network and survey data from two women’s prisons in Pennsylvania ( N = 223) (WO-PINS), we find that pseudo-family–based, friendship-based, and trust-based network ties formed during incarceration are associated with reduced stress among incarcerated women. However, we find limited evidence that perceptions of social integration mediate the relationship between prison network ties and stress, suggesting that prison network ties are associated with stress reduction independent of an individual’s perception of integration.

Deep Learning-Based Prediction of Daily COVID-19 Cases Using X (Twitter) Data.

Due to the importance of COVID-19 control, innovative methods for predicting cases using social network data are increasingly under attention. This study aims to predict confirmed COVID-19 cases using X (Twitter) social network data (tweets) and deep learning methods. We prepare data extracted from tweets by natural language processing (NLP) and consider the daily G-value (growth rate) as the target variable of COVID-19, collected from the worldometer. We develop and evaluate a time series mixer (TSMixer) predictive model for multivariate time series. The mean squared error (MSE) loss on the test dataset was 0.0063 for 24-month Gvalue prediction when using the MinMax normalization with recursive feature elimination (RFE) and average or min aggregation method. Our findings illuminate the potential of integrating social media data to enhance daily COVID-19 case predictions and are applicable also for epidemiological forecasting purposes.

KG-CFSA: a comprehensive approach for analyzing multi-source heterogeneous social network knowledge graph

Analyzing opinions, extracting and modeling information, and performing network analysis in online information studies are challenging tasks with multi-source social network data. This complexity arises from the difficulty in harnessing data across various platforms and the absence of a unified data modeling approach. Although social network analysis has used a multiplex approach to study complex networks, no previous work has integrated data from multiple social networks, knowledge graph fusion, and contextual focal structure analysis (CFSA) for an online study. This study has developed a multi-source graph model and applied a Cartesian merge to model relations across multiple documents, entities, and topics. We improved the information modeled with third-party data sources such as WikiData and DiffBot. This approach has created a multiplex network instance for CFSA detection, incorporating topic-topic, entity-entity, and document-document models. We applied this method to a dataset from the Indo-Pacific region and identified 40,000 unique focal sets of influential topics, entities, and documents. The top sets discussed economics, elections, and policies such as the Indo-Pacific Economic Framework, Ekonomi baru, #NKRIHargaMati, #IndonesiaJaya, and the Xinjiang Supply Chain. Our model tracks information spread across multiple social media platforms and enhances the visibility of vital information using various relationships. The results underscore the effectiveness of KG-CFSA in contextualizing large-scale information from multiple sources.

Resilience or Risk? Evaluating Three Pathways Linking Hispanic Immigrant Networks and Health.

There are competing perspectives on the impact of Hispanic immigrants' social networks on health; the Hispanic health paradox views networks as sources of resilience, whereas the tenuous ties perspective views networks as sources of risk. In this study, I explore the effect of networks on health by examining three network pathways: social capital, social bonding, and network stress. Using egocentric social network data from the VidaSana Study, a survey of 547 Hispanic immigrants in Indiana, I investigate how each network pathway is associated with physical health, mental health, and health care utilization. Results show that networks with greater capital, namely, more network health knowledge, promote physical health and health care access, whereas social bonding, operationalized as close and dense networks, benefits mental health and health care utilization. Network stress contributes to worse mental health yet improved health care access. Implications for social networks and health research among the Hispanics and more broadly are discussed.

Navigating Complex Relationships: Support Networks Among Women in Community Corrections

In this article, we explored the social networks of 20 women who were in the process, or had completed, a sentence at a residential community corrections facility. Drawing on egocentric social network data and in-depth qualitative interviews, we analyzed the kinds of support that were most and least available to women, who were members of their network and what type of support they provided, and the role of complex relationships and peers. We found that women often relied on complex relationships and strategically navigated these relationships to access support. Many women also expressed a desire to mend and heal damaged relationships, recognizing their significance in their support system. Although peers can play a critical role in providing support to system-involved women, community corrections must invest in facilitating supportive connections and relationships among women. Ultimately, this research offers insights that can guide community corrections organizations in building and repairing women’s networks.

Natural language processing of social network data for the evaluation of agricultural and rural policies

Global sustainable development challenges affect the agricultural sector, and many innovations aimed at addressing these challenges have been introduced in the agri-food sector. In this complex context, new agricultural policies are being implemented in Europe. Their success depends on their potential to adapt to new realities, responding to the opinions and demands of the European population. Given the rapid rise of social media as an important part of people's daily lives, public administrations have introduced digitalization and communication strategies through social media sites. Social media can provide policymakers with large amounts of data on user opinions. Given the value of social media as a rich source of data on public views and opinions, the aim of this paper is twofold: (i) to use natural language processing (NLP) to identify the events that have led to negative or positive opinion about European Common Agricultural Policy (CAP) reform and (ii) to evaluate the ability of NLP to study users' opinions on Twitter/X. The findings show that issues such as Brexit, the European Green Deal, the role of CAP in the environment, livestock farming, food safety, and illegal practices and corruption in the distribution of CAP funds have crucial implications for the design and application of the new CAP. Moreover, the study also suggests that NLP techniques can provide opportunities to integrate agricultural policies and instruments in the agri-food sector by assessing society's opinions. Sentiment analysis, even considering its limitations, could support sound and inclusive policymaking approaches anticipating public opinion in cases of risk of social unrest.

Environmental, social, and governance and hierarchical network data envelopment analysis firm efficiencies of Japan Airlines' supply chain

AbstractAlthough environmental, social, and governance (ESG) have been recognized for its overall impact on firm efficiency, research on the effects of the three main and multiple sub elements of ESG, especially in the airline industry, has been lacking. Thus, we analyze the impacts of overall ESG, its three main elements, and each sub elements of ESG on the firm efficiency of 29 suppliers, partners, and customers of Japan Airlines over the period of 2013–2022. First, we employ a two‐stage hierarchical network data envelopment analysis (DEA) technique that assesses the interrelationships and interdependencies among the supply chain players in contributing toward achieving their respective operating and profitability efficiencies. Second, we run ordinary least squares regression analyses with 5000 bootstrap replications and determine that overall ESG and its three main elements are positively linked with firm efficiencies. The sub elements of ESG have different impacts on firm efficiencies. That is, resource use and environmental innovation under the Environmental element and human rights and product responsibility under the Social element show significantly positive associations with firm efficiencies. All Governance sub elements positively affect firm efficiencies. The outcomes of this study will be valuable for managers at Japan Airlines and other policymakers within its supply chain because it highlights the importance of focusing on the three main and sub elements of ESG and employing the accurate firm efficiency measurement method when interrelationships and interdependencies of decision‐making units exist.