Social Networks最新文献

{"title":"Two-mode network autoregressive model for network analysis with core nodes","authors":"Huiyun Tang ,&nbsp;Moxuan Mi ,&nbsp;Yingying Ma ,&nbsp;Haisheng Yang ,&nbsp;Feifei Wang","doi":"10.1016/j.socnet.2026.01.004","DOIUrl":"10.1016/j.socnet.2026.01.004","url":null,"abstract":"<div><div>In recent decades, there is an increasing interest in analyzing two-mode networks, which are constructed by two types of nodes. In two-mode networks, the <em>core nodes</em> (such as the superstars in social platforms) are often encountered in practice. These core nodes could generate different network influences compared to ordinary nodes. Then considering the effect of core nodes in network analysis becomes an important problem. To address this problem, we propose a novel network autoregressive model for two-mode networks with core nodes. It assumes each type of nodes can be split into the <em>core group</em> and the <em>ordinary group</em>. Then a network autoregressive model with different cross-mode effects for the core group and the ordinary group is established. We further extend this model to incorporate the interaction effects between different groups of nodes (e.g., the core group of Type I and the ordinary group of Type II). The theoretical properties of the proposed models are investigated. The finite sample performance is assessed through a variety of simulations. Finally, we apply the proposed models to a real security dataset to explore the influences between fund performance and analysts.</div></div>","PeriodicalId":48353,"journal":{"name":"Social Networks","volume":"86 ","pages":"Pages 75-87"},"PeriodicalIF":2.4,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146189496","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From survey data to social multiplex models: Incorporating interlayer correlation from multiple data sources","authors":"Alec Fluer ,&nbsp;Ian Laga ,&nbsp;Logan Graham ,&nbsp;Ellen Almirol ,&nbsp;Makenna Meyer ,&nbsp;John A. Schneider ,&nbsp;Breschine Cummins","doi":"10.1016/j.socnet.2026.01.005","DOIUrl":"10.1016/j.socnet.2026.01.005","url":null,"abstract":"<div><div>Multiplex networks are useful social models when different types of connections exist between people, such as friend ties or sexual partner ties. Each layer in a multiplex represents a distinct connection type, and the tendency of individuals to form ties with similar individuals (homophily) can induce correlation and overlapping ties between layers. This overlap can be important in dynamical processes that evolve within the social system, such as epidemic spread. In this work, we extend Social Distance Attachment (SDA) and the Social Distance Configuration model (SDC) to multiplexes. SDA captures connection probabilities induced by homophily, which in many cases can be measured from survey or census data, and SDC integrates these probabilities into the well-known configuration model to sample networks with a prescribed degree sequence. Our extension is called the Social Distance Configuration model with Degree Preservation (SDC-DP), and it compensates for the unexpected loss of hub nodes in SDC when the configuration model with subtraction is used. We combine SDC-DP with a method for sampling correlated degree sequences between multiplex layers from survey statistics. We demonstrate our method on synthetic data and on survey data from the uConnect study [Schneider et al. (2017)], which was performed in the Chicago area among a vulnerable population. We find that substantial increases in overlap can be induced between the layers of a multiplex by incorporating homophily and interlayer degree correlation.</div></div>","PeriodicalId":48353,"journal":{"name":"Social Networks","volume":"86 ","pages":"Pages 104-119"},"PeriodicalIF":2.4,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146189494","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Using LASSO for variable selection in exponential random graph models","authors":"Sergio Buttazzo,&nbsp;Göran Kauermann","doi":"10.1016/j.socnet.2025.12.007","DOIUrl":"10.1016/j.socnet.2025.12.007","url":null,"abstract":"<div><div>Exponential Random Graph Models (ERGMs) are a powerful and flexible framework for modeling network data. A fundamental challenge in ERGM estimation is the correct specification of the (sufficient) statistics that define the model structure. This paper addresses the problem of variable selection in ERGMs by making use of LASSO, a penalized estimation technique that shrinks some parameter estimates to zero, effectively selecting relevant variables. While LASSO is well established in standard regression settings, its application to ERGMs remains less explored. Here, we demonstrate how LASSO can be employed in the ERGM framework to perform variable selection and propose a ranking procedure to assess the relevance of candidate model terms.</div></div>","PeriodicalId":48353,"journal":{"name":"Social Networks","volume":"86 ","pages":"Pages 1-11"},"PeriodicalIF":2.4,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145886345","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Estimating unknown populations from informant reports using scale-up reference groups and capture-recapture inference","authors":"Scott Feld,&nbsp;Alec McGail","doi":"10.1016/j.socnet.2026.01.003","DOIUrl":"10.1016/j.socnet.2026.01.003","url":null,"abstract":"<div><div>The network scale-up method has long been used to estimate the size of hard-to-reach populations by leveraging the fact that individuals often know members of these groups. By sampling from a frame population and asking respondents how many people they know in both the target group and a reference group of known size, researchers can infer the size of the hidden population. This approach relies on the assumption that, on average, members of both groups are equally likely to be reported by respondents. However, estimating the average visibility of a hard-to-count group can be particularly challenging. An alternative approach adapts the capture-recapture method, originally developed for wildlife populations, to informant reports. Yet, such estimates depend on strong and often questionable assumptions about the probabilities of capture and recapture. In this paper, we introduce a method that calibrates scale-up estimates using the frequencies of “recapture.” This method can also be seen as calibrating capture-recapture estimates using reference groups from the scale-up approach. Our method assumes that the distributions of the number of reports per group member are similarly shaped for both the target and reference groups—specifically, that the ratio of the variance to the square of the mean is approximately equal across groups—even when the target group’s mean and full distribution remain unknown. We propose that this approach is particularly well-suited when the target group resembles a reference group but differs in its overall “visibility” to informants, whether due to stigma, social concealment, or varying degrees of prominence. We demonstrate the utility of this method using Facebook friends of upperclassmen to estimate the size of the freshman population at 100 universities. We examine the conditions under which our approach is most effective and identify key issues that warrant further theoretical and empirical investigation.</div></div>","PeriodicalId":48353,"journal":{"name":"Social Networks","volume":"86 ","pages":"Pages 35-41"},"PeriodicalIF":2.4,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146189495","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Investigating the impacts of missing data mechanims and treatments with latent space models","authors":"Tracy M. Sweet ,&nbsp;Xin Qiao ,&nbsp;Ashani Jayasekera ,&nbsp;Yishan Ding","doi":"10.1016/j.socnet.2026.01.002","DOIUrl":"10.1016/j.socnet.2026.01.002","url":null,"abstract":"<div><div>Studies on missing network data have largely focused on the impact of missing data on network structure rather than inference from a statistical model. In particular, there has very little research on the impact of missing data when fitting latent variable network models, so we examined the impact of common missing data mechanisms and subsequent missingness treatment and imputation methods when working with latent variable network models, focusing on the latent space model (Hoff et al., 2002). By removing the common definitions of missingness, our simulation study found large differences in inference, parameter, and network feature recovery based on the missingness mechanism and treatment method. In addition, we induced missingness using a real-world dataset and explored how treatment methods impacted subsequent inference and network recovery. We found that missingness based on a node covariate that also predicted network ties was the most problematic form of missingness and that complete case analysis and Bayesian estimation generally worked as well or better than other methods.</div></div>","PeriodicalId":48353,"journal":{"name":"Social Networks","volume":"86 ","pages":"Pages 42-61"},"PeriodicalIF":2.4,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146189491","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The influence of social network on consumers’ negative reactions toward corporate social advocacy: An egocentric network analysis","authors":"Xueying Zhang ,&nbsp;Ting Wang","doi":"10.1016/j.socnet.2025.12.008","DOIUrl":"10.1016/j.socnet.2025.12.008","url":null,"abstract":"<div><div>This study investigates how consumers’ real life social networks affect their intentions to engage in negative word-of-mouth (NWOM) and boycott behaviors when confronted with a brand’s Corporate Social Advocacy (CSA) that contradicts their preexisting attitudes toward the issue. A total of 178 participants completed an online egocentric network survey, which included 604 reported alters. The results suggest individuals’ intentions of NWOM and boycott are predominantly shaped by the attitudes of alters in the network, rather than the size of the network or network density. Anger and contempt significantly facilitate the impact of network characteristics on NWOM and boycott. The findings highlight that cohesion amplifies conformity, but it is shared meaning and affective resonance that ultimately motivate behavior.</div></div>","PeriodicalId":48353,"journal":{"name":"Social Networks","volume":"86 ","pages":"Pages 12-22"},"PeriodicalIF":2.4,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145940547","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Centrality in directed networks","authors":"Gordana Marmulla,&nbsp;Ulrik Brandes","doi":"10.1016/j.socnet.2026.01.001","DOIUrl":"10.1016/j.socnet.2026.01.001","url":null,"abstract":"<div><div>The identification of important nodes in a network is a pervasive task in a variety of disciplines from sociology and bibliometry to geography and chemistry, and an ever growing number of centrality indices is proposed for this purpose. While such indices are often ad-hoc, preservation of the vicinal preorder has been identified as the core axiom shared by centrality rankings on undirected graphs. We extend this idea to directed graphs by defining vertex preorders based on directed neighborhood-inclusion criteria. While, for the undirected case, the vicinal preorder is total on threshold graphs and preserves all standard centrality indices, we show that our generalized preorders are total on certain subclasses of threshold digraphs. We thus provide a consistent formalization of the hitherto rather conceptual notions of radial, medial, and hierarchical centralities. Through the criteria different notions of centrality are distinguishable, as we exemplify with selected standard centrality indices.</div></div>","PeriodicalId":48353,"journal":{"name":"Social Networks","volume":"86 ","pages":"Pages 23-34"},"PeriodicalIF":2.4,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145940548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Closing the loop: Design, implementation, and evaluation of a regular-feedback network intervention for social connectedness and mental health","authors":"Mohammad Khalilian ,&nbsp;Anthony R. Bardo ,&nbsp;Claire M. Reardon ,&nbsp;Amy Kostelic ,&nbsp;Susie Thiel ,&nbsp;Robert W. Krause","doi":"10.1016/j.socnet.2026.02.002","DOIUrl":"10.1016/j.socnet.2026.02.002","url":null,"abstract":"<div><div>Persistent increases in social isolation pose significant public health challenges, yet community interventions rarely leverage social network analysis longitudinally. Most network interventions rely on limited diagnostics. This study introduces and evaluates an adaptive intervention where longitudinal network data iteratively informed program design in real-time. Over eight weeks, we collected weekly sociocentric and ethnographic data from an intergenerational group of women participating in a creative movement program to enhance meaningful social connections and improve mental health outcomes. We used these data to guide weekly group pairings to increase cohesion, reciprocal relations, and intergenerational connections. The intervention’s effects on tie formation and maintenance were assessed using Stochastic Actor-Oriented Models (SAOMs), and mental health outcomes were compared to a control group. Results show that while adaptive group pairings facilitated the creation of new close ties, their impact on maintaining existing ties was limited. The intervention group experienced improvements in mental health compared to controls. This study demonstrates the value of a real-time, feedback-driven approach, moving network interventions from a limited diagnostic tool to an adaptive process. Our findings highlight the value of embedding longitudinal network designs into active program implementation and underscore the distinction between the mechanisms governing tie formation and maintenance.</div></div>","PeriodicalId":48353,"journal":{"name":"Social Networks","volume":"86 ","pages":"Pages 88-103"},"PeriodicalIF":2.4,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146189493","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Who benefits most? Intervention-induced changes in the social networks of people living with dementia","authors":"Doris Gebhard,&nbsp;Jan Ellinger","doi":"10.1016/j.socnet.2026.01.006","DOIUrl":"10.1016/j.socnet.2026.01.006","url":null,"abstract":"<div><div>For most people living with dementia, their social network shrinks as the disease progresses, especially when they move into a care home. Many experience major barriers to build social relationships in the new living environment and additionally there is a lack of effective interventions to promote social contacts between residents. Considering this, the aim of the present study is twofold: (1) to investigate the effect of two interventions (physical activity [PA] vs. PA plus social component [PAS]) on the social networks of people living with dementia in long-term care facilities using an ordinal mixed-effects model, and (2) to identify the participants who benefit most from these interventions through descriptive profile analysis. Sociocentric networks of the intervention groups were assessed before and after the respective 12-week interventions. Photographs served as a facilitative tool, enabling participants to identify their social contacts and evaluate the quality of these relationships, categorizing them as positive regard, casual friend, or true friend. Loneliness, the importance of friendships within the facility and the attitude towards peer residents were assessed in interviews. 46 people living with dementia (87.1 ± 7.3 years, 82.6 % female) from six care homes participated in the interventions. In five out of six social networks, both graph density and weighted graph density increased. The average graph density across the PA groups increased by 14.8 % and by 153.3 % in the PAS groups. The results of the ordinal regression analysis confirm a significant positive time effect across both intervention types (β = 2.29, 95 % CI = [1.36; 3.86]) as well as for each intervention type separately. Evident interaction effects (β = 5.76, 95 % CI = [2.87; 11.57]) indicate that the time effect in the PAS groups (β = 10.68, 95 % CI = [6.11; 18.69]) was significantly higher than in the PA groups (β = 2.61, 95 % CI = [1.47; 4.63]). The profile analysis indicates that a higher level of cognitive functioning in particular contributes to greater benefit. The observed results fit in well with the current state of research and at the same time underline the benefits and necessity of using social network analysis approaches in research with people living with dementia in the long-term care setting.</div></div>","PeriodicalId":48353,"journal":{"name":"Social Networks","volume":"86 ","pages":"Pages 62-74"},"PeriodicalIF":2.4,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146189492","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dissipation and bondedness in networks via conflict-based cohesion","authors":"Kenneth S. Berenhaut ,&nbsp;Liangdongsheng Lyu ,&nbsp;Yuxiao Zhou","doi":"10.1016/j.socnet.2025.12.003","DOIUrl":"10.1016/j.socnet.2025.12.003","url":null,"abstract":"<div><div>In this paper, we introduce a method to measure the extent to which individual ties in a social network contribute to cohesiveness in subgroups through consideration of heterogeneity in local/global connectedness. Employing the concept of (conflict-based) cohesion introduced recently by Berenhaut, Moore and Melvin [<em>Proceedings of the National Academy of Sciences</em>, <strong>119</strong> (4) (2022)], we define a measure of dissipation of cohesion over edges, as well as an accompanying local threshold which distinguishes <em>dissipative</em> from <em>bonded</em> ties. The resulting network of bonded edges can provide structural connectivity information which does not suffer from some typical resolution issues, while the network of dissipative ties can be used to identify regions of network vulnerability and possible fission. Importantly, the method can identify crucial and intermediary <em>independent</em> nodes, which may be informative in social and other settings. Applications to real-world data including two-mode networks are considered.</div></div>","PeriodicalId":48353,"journal":{"name":"Social Networks","volume":"85 ","pages":"Pages 108-120"},"PeriodicalIF":2.4,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145839310","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}