Search

Influence maximization (IM) is crucial for recommendation systems and social networks. Previous research primarily focused on static networks, neglecting the homophily and dynamics inherent in real-world networks. This has led to inaccurate simulations of information spread and influence propagation between nodes, with traditional IM algorithms' selected seed node sets failing to adapt to network evolution. To address this issue, this paper proposes a homophilic and dynamic influence maximization strategy based on independent cascade model (HDIM). Specifically, HDIM consists of two components: the seed node selection strategy that accounts for both homophily and dynamics (SSHD), and the independent cascade model based on influence homophily and dynamics (ICIHD). SSHD strictly constrains the proportions of different node types in the seed node set and can flexibly update the seed node set when the network structure changes. ICIHD redefines the propagation probabilities between nodes, adjusting them in response to changes in the network structure. Experimental results demonstrate HDIM's excellent performance. Specifically, the influence range of HDIM exceeds that of state-of-the-art methods. Furthermore, the proportions of various activated nodes are closer to those in the original network. [ABSTRACT FROM AUTHOR]

Preferences for homogamous partnerships, not only in terms of having a partner with the same ethnicity, but one with the same religion, are an important factor in explaining low levels of interethnic partnerships in Western countries. However, previous research has rarely explicitly focused on the role of preferences for partnership formation patterns. Using data from a factorial survey experiment, which was implemented in the 9th wave of the "Children of Immigrants Longitudinal Survey in Four European Countries" among young adults in Germany (CILS4EU-DE), this study explores patterns of religious homophily in partnership preferences among young adults in Germany. It thereby specifically focuses on individuals belonging to two major religious groups: Christians and Muslims. It investigates the effects of religious denomination, religiosity, type of intimate partnership, and gender differences for religious homophily in partnership preferences. Both male and female respondents were found to prefer partners of the same religious denomination, with this effect being stronger among Muslims than Christians. Muslim respondents showed no or little disapproval of more strongly religious partners, whereas Christian respondents showed strong disapproval of more religious partners. Among Christian and male Muslim but not among female Muslim respondents, preferences for religious homophily were lower for casual partnerships than for marriage. Overall, the findings suggest that religious homophily and religion play an important part in shaping partnership choices among young Christian and Muslim adults in Germany. [ABSTRACT FROM AUTHOR]

Copyright of Service Industries Journal is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

AbstractWith the recent gradual reduction in negative perceptions of virtual influencers (VIs), understanding how consumers perceive VIs’ anthropomorphism and its impact on forming consumer relationships is critical for increasing marketing effectiveness. To gain a better understanding of how consumers form relationships with VIs, this study examined VI characteristics as well as consumer personalities. The study’s data were collected from a sample of 266 social media users. The results show that VI’s anthropomorphism positively affected the parasocial relationship (PSR). This association was reinforced by homophily, whereas the neede for uniqueness dampened it. PSR positively influenced trust, intention to imitate, and word-of-mouth (WOM). Moreover, trust positively affected imitation intention and WOM. This study aimed to broaden theoretical understanding, specifically on consumers’ responses to VIs, which is an emerging research area, while providing practical recommendations for companies incorporating VIs into their strategies. [ABSTRACT FROM AUTHOR]

Graph Neural Network (GNN) is an effective model for processing graph-structured data. Most GNNs are designed to solve homophilic graphs, where all nodes belong to the same category. However, graph data in real-world applications are mostly heterophilic, and homophilic GNNs cannot handle them well. To address this, we propose a novel hybrid-learning framework based on Node Homophily and Spectral Heterophily (NHSH) for node classification in graph networks. NHSH is designed to achieve state-of-the-art or superior performance on both homophilic and heterophilic graphs. It includes three core modules: homophilic node extraction (HNE), heterophilic spectrum extraction (HSE) and node feature fusion (NFF). More specifically, HNE identifies symmetric neighborhoods of nodes with the same category, extracting local features that reflect these symmetrical structures. Then, HSE uses filters to analyze the high and low-frequency information of nodes in the graph and extract the global features of the nodes. Finally, NFF fuses the above two node features to obtain the final node features in graphs. Moreover, an elaborate loss function drives the network to preserve critical symmetries and structural patterns in the graph. Experiments on eight benchmark datasets validate that NHSH performs comparably or better than existing methods across diverse graph types. [ABSTRACT FROM AUTHOR]

Social prejudice, family nonacceptance, and lack of marriage or adoption rights often restrict the formation of conventional social ties among LGBT older adults. As a result, they often rely on families of choice constituted by other LGBT/age peers for support. Using a series of regression analyses with a national sample of LGBT older Americans, this study investigated how characteristics of social network structure (size and composition - LGBT vs. non-LGBT identity and age ≥50 vs. < 50) were related to LGBT older adults' social network function (perceived social support). Larger social networks, especially those composed of LGBT members and older adults, were associated with more perceived social support. In subgroup analyses, larger social networks composed of more LGBT members and older adults were associated with more perceived social support among lesbian and gay respondents. For bisexual + older adults, larger social network size was associated with more perceived social support, but social network composition was not related to more perceived social support. For transgender older adults, neither social network size nor network composition were significantly associated with perceived social support. This study demonstrated that having more people with similar characteristics in their social networks cues LGBT older adults about the availability of social support. Findings may inform strategies for tailoring programs intended to maintain and strengthen LGBT older adults' social support networks. [ABSTRACT FROM AUTHOR]

Policy actors (PAs) like nongovernmental organizations, political parties or governmental institutions strategically communicate on social media to gain attention and thus influence the public agenda. We argue that networks of PAs engaged in the same issues (i.e., a PA's peer network) are crucial to attracting the interest of a broad audience. Drawing on network theory, we posit that (i) ideological homophily, and (ii) the centrality and embeddedness in a PA's peer network increase the attention received from all Twitter (now X) users. We investigate these premises by analyzing the European migration discourse on Twitter (2014–2020). The results of our study reveal that the centrality of PAs in their peer networks and ideologically similar relations considerably increase attention from the whole Twittersphere. These findings provide strong evidence that a PA's role in its organizational peer network on social media governs the attention received in the overall discourse. [ABSTRACT FROM AUTHOR]

The proliferation of robot accounts on social media platforms has posed a significant negative impact, necessitating robust measures to counter network anomalies and safeguard content integrity. Social robot detection has emerged as a pivotal yet intricate task, aimed at mitigating the dissemination of misleading information. While graph-based approaches have attained remarkable performance in this realm, they grapple with a fundamental limitation: the homogeneity assumption in graph convolution allows social robots to stealthily evade detection by mingling with genuine human profiles. To unravel this challenge and thwart the camouflage tactics, this work proposed an innovative social robot detection framework based on enhanced HOmogeneity and Random Forest (HORFBot). At the core of HORFBot lies a homogeneous graph enhancement strategy, intricately woven with edge-removal techniques, to meticulously dissect the graph into multiple revealing subgraphs. Subsequently, leveraging the power of contrastive learning, the proposed methodology meticulously trains multiple graph convolutional networks, each honed to discern nuances within these tailored subgraphs. The culminating stage involves the fusion of these feature-rich base classifiers, harmoniously aggregating their insights to produce a comprehensive detection outcome. Extensive experiments on three social robot detection datasets have shown that this method effectively improves the accuracy of social robot detection and outperforms comparative methods. [ABSTRACT FROM AUTHOR]

This research examines how similarities in educational and ethnic backgrounds (status homophily), between word of mouth (WOM) participants, influences the effectiveness of received offline WOM on the recipient's behavioural intentions. The educational similarity between individuals is conceptualized as acquired homophily, whereas ethnic similarity is defined as ascribed homophily. This study employs scenario-based experiments, and the results suggest that positive and negative WOM received from homophilous sources is more effective in influencing the recipient's purchase and WOM re-transmission intentions than recommendations received from heterophilous sources. This research expands the literature about offline WOM and the multidimensional status-homophily construct by providing insights on the differential influence of positive and negative recommendations received from WOM sources similar or dissimilar to the WOM recipients in terms of their educational and ethnic backgrounds. This is important from both the theoretical and practitioner perspective as the recent focus of scholarly research is on understanding the relationship between online homophily and e-WOM at the expense of offline WOM-homophily relationship. [ABSTRACT FROM AUTHOR]

Artificial Intelligence (AI) chatbots, such as ChatGPT, have been shown to mimic individual human behaviour in a wide range of psychological and economic tasks. Do groups of AI chatbots also mimic collective behaviour? If so, artificial societies of AI chatbots may aid social scientific research by simulating human collectives. To investigate this theoretical possibility, we focus on whether AI chatbots natively mimic one commonly observed collective behaviour: homophily, people's tendency to form communities with similar others. In a large simulated online society of AI chatbots powered by large language models (N = 33,299), we find that communities form over time around bots using a common language. In addition, among chatbots that predominantly use English (N = 17,746), communities emerge around bots that post similar content. These initial empirical findings suggest that AI chatbots mimic homophily, a key aspect of human collective behaviour. Thus, in addition to simulating individual human behaviour, AI‐powered artificial societies may advance social science research by allowing researchers to simulate nuanced aspects of collective behaviour. [ABSTRACT FROM AUTHOR]

Objective: This study investigates the intersection of gender and social class in determining individual access to social capital in Spain. Specifically, the study aims to examine how gender and class homophily influence the formation and composition of personal networks. Methods: The study employs a quantitative approach, using survey data from a representative sample of the Spanish population. It analyzes the relationship between gender, social class, network size, and composition, leveraging a neocapital framework and considering the expected returns on social capital investments. Results: The findings reveal a significant gender gap in social capital, particularly among the upper classes. Women, especially those from working‐class origins, have limited access to upper‐class networks compared to men with similar mobility experiences. These results highlight the reinforcing effects of class and gender homophily on social capital inequalities. Conclusions: The study concludes that gender and class intersect to shape individuals' access to social capital in Spain. Homophily plays a crucial role in reinforcing privilege and limiting opportunities for women, particularly in the upper social strata. These findings underscore the need for policies and interventions to address gender discrimination and promote greater inclusivity in social networks. [ABSTRACT FROM AUTHOR]

Background and Objectives: Homophily represents the extent to which people feel others are like them and encourages the uptake of activities they feel people like them do. Currently, there are no data on blood donor homophily with respect to (i) people's representation of the average prototypical UK blood donor and (ii) the degree of homophily with this prototype for current donors, non‐donors, groups blood services wish to encourage (ethnic minorities), those who are now eligible following policy changes (e.g., men‐who‐have‐sex‐with‐men: MSM) and recipients. We aim to fill these gaps in knowledge. Materials and Methods: We surveyed the UK general population MSM, long‐term blood recipients, current donors, non‐donors and ethnic minorities (n = 785) to assess perceptions of the prototypical donor in terms of ethnicity, age, gender, social class, educational level and political ideology. Homophily was indexed with respect to age, gender and ethnicity. Results: The prototypical UK blood donor is perceived as White, middle‐aged, middle‐class, college‐level educated and left‐wing. Current donors and MSM are more homophilous with this prototype, whereas recipients and ethnic minorities have the lowest homophily. Higher levels of homophily are associated with an increased likelihood of committing to donate. Conclusion: The prototype of the UK donor defined this as a White activity. This, in part, may explain why ethnic minorities are less likely to be donors. As well as traditional recruitment strategies, blood services need to consider broader structural changes such as the ethnic diversity of staff and co‐designing donor spaces with local communities. [ABSTRACT FROM AUTHOR]

Video blogging channels for social media technology continue to innovate and evolve, and brands are beginning to rely on social media channels for product marketing. The factors influencing consumers' purchase intention for products advertised by video bloggers are numerous and unclear. The main purpose of this study is to explore the mechanism by which the characteristics of video bloggers influence the formation of emotional cognition and then influences consumers' purchase intention. Based on the SOR model, 518 questionnaires were administered to Chinese video blogging users. The AMOS 24.0 and SPSSAU 24.0 web tools were used to analyze the study data. Empirical results indicate that consumers' perceived homogeneity, expertise, degree of emotional attachment to video bloggers, and perceived source confidence have a direct or indirect positive influence on purchase intentions. Evident advertising intention weakens the relationship between emotional attachment and purchase intention. This result is strategically important for a brand's advertising efforts and market share and provides new research insights and frameworks for studying consumers' advertised product purchase behaviors in the context of video blogging channels for social media. [ABSTRACT FROM AUTHOR]

This paper provides a quick survey of results on the classic SIR model and variants allowing for heterogeneity in contact rates. It notes that calibrating the classic model to data generated by a heterogeneous model can lead to forecasts that are biased in several ways and to understatement of the forecast uncertainty. Among the biases are that we may underestimate how quickly herd immunity might be reached, underestimate differences across regions, and have biased estimates of the impact of endogenous and policy-driven social distancing. [ABSTRACT FROM AUTHOR]

Social relations between demographically dissimilar people are less likely to last. But up till now, why relations with dissimilar friends, confidants, or even sport partners are less stable has remained unclear. We argue that the faster dissolution of ties to dissimilar others may stem from their weaker embeddedness in our social networks. We may feel less emotionally close to those who differ from us in key social dimensions such as gender, age, and education, and these alters may fulfill fewer roles (e.g., friend and study partner, or ‘multiplexity’). Moreover, their dissimilarity may hinder their ability to form relations with others in our social network. In this contribution, we investigate the impact of ego‐alter dissimilarity on the stability of friendships, confidants, and study and sport relations, while acknowledging multiplexity—recognizing that the same alter may serve different roles. We find that ego‐alter age dissimilarity is associated with tie dissolution; relations are less stable and consistently so across emotional and instrumental network layers. Gender and education dissimilarity do not impact relationship stability among our sample of Dutch students. The better alters are embedded in ego's network, the more stable are their ties. Relational embeddedness (i.e., emotional closeness and role overlap) predominantly affects the stability of confidants and friendship relations; structural embeddedness (i.e., alters having ties to ego's other alters) predominantly affects the stability of study relations. This also explains why relations with differently aged alters are less stable. [ABSTRACT FROM AUTHOR]

The rise of social media has correlated with an increase in political polarization, which many perceive as a threat to public discourse and democratic governance. This paper presents a framework, drawing on social epistemology and the economic theory of public goods, to explain how social media can contribute to polarization, making us collectively poorer, even while it provides a preferable media experience for individual consumers. Collective knowledge and consensus is best served by having richly connected networks that are epistemically integrated: individuals with diverse levels of expertise should be relatively well connected to each other. In epistemically segregated networks, by contrast, we have reason to predict collective epistemic failures. Expert knowledge will be isolated from the majority, leading average opinion to be less informed than is socially optimal, and entrenching disagreements. Because social media enables users to very easily adopt homophilous network connections – connections to those with similar opinions, education levels, and social backgrounds – it is likely to have increased epistemic segregation compared to older media platforms. The paper explains the theoretical foundations of these predictions, and sketches regulatory measures – such as taxes – that might be employed to preserve the public good of a well integrated social media network. [ABSTRACT FROM AUTHOR]

We present a model of online content sharing where agents sequentially observe an article and decide whether to share it with others. This content may or may not contain misinformation. Each agent starts with an ideological bias and gains utility from positive social media interactions but does not want to be called out for propagating misinformation. We characterize the (Bayesian–Nash) equilibria of this social media game and establish that it exhibits strategic complementarities. Under this framework, we study how a platform interested in maximizing engagement would design its algorithm. Our main result establishes that when the relevant articles have low-reliability and are thus likely to contain misinformation, the engagement-maximizing algorithm takes the form of a "filter bubble"—creating an echo chamber of like-minded users. Moreover, filter bubbles become more likely when there is greater polarization in society and content is more divisive. Finally, we discuss various regulatory solutions to such platform-manufactured misinformation. [ABSTRACT FROM AUTHOR]

Research on race homophily in the United States has yet to meaningfully include the growing multiracial population. The present study confronts this challenge by drawing upon recent conceptualizations of race as a multidimensional construct. In aligning this insight with current understandings of homophily, we identify and address several open questions about the origins of race homophily—namely regarding the possibility of peer influence on racial identity and network selection based on multiple facets of race. Data are from 3,036 youth in two large U.S. high schools with sizable proportions of mixed-race students. Using a stochastic actor-oriented model, we find that students choose friends based on similarity across multiple dimensions of racial identity and that peer influence operates to reinforce multiracial youths' racial self-classification rather than to induce change. This points to a system where race homophily arises through multiple selection mechanisms and is reinforced by pressure toward conformity.

We explore the interplay between homophilic preferences, reciprocity, and societal values in the formation of venture capital investment syndicates in China. Both Chinese and U.S. syndicate lead firms generally prefer including their fellow compatriot firms over comparable non-compatriots in the investment syndicates that they assemble. When a Chinese firm initiates a collaborative first move by including a U.S. firm in an investment syndicate, however, the U.S. firm no longer prefers comparably familiar U.S. firms over the Chinese firm when it subsequently chooses among prospective syndicate partner firms to include in its investment syndicates. In such cases, familiarity triggers impartiality; the experiential trust that was garnered from the collaborative first-move engagement initiated by the Chinese firm diminishes the nationality-based homophilic preferences of the U.S. firm. We do not find similar dynamics when the tables are turned. When a U.S. firm initiates a collaborative first move by including a Chinese firm in an investment syndicate, the Chinese firm subsequently remains partial to fellow compatriot firms that are otherwise comparable to the U.S. firm. The homophilic preferences and identity-based trust between Chinese firms grounded in shared nationality are resilient to any goodwill created by U.S. firms when they initiate collaborative first moves. [ABSTRACT FROM AUTHOR]

Video blogging channels for social media technology continue to innovate and evolve, and brands are beginning to rely on social media channels for product marketing. The factors influencing consumers’ purchase intention for products advertised by video bloggers are numerous and unclear. The main purpose of this study is to explore the mechanism by which the characteristics of video bloggers influence the formation of emotional cognition and then influences consumers’ purchase intention. Based on the SOR model, 518 questionnaires were administered to Chinese video blogging users. The AMOS 24.0 and SPSSAU 24.0 web tools were used to analyze the study data. Empirical results indicate that consumers’ perceived homogeneity, expertise, degree of emotional attachment to video bloggers, and perceived source confidence have a direct or indirect positive influence on purchase intentions. Evident advertising intention weakens the relationship between emotional attachment and purchase intention. This result is strategically important for a brand’s advertising efforts and market share and provides new research insights and frameworks for studying consumers’ advertised product purchase behaviors in the context of video blogging channels for social media.

Abstract Social network analysis and shared-patient physician networks have become effective ways of studying physician collaborations. Assortative mixing or “homophily” is the network phenomenon whereby the propensity for similar individuals to form ties is greater than for dissimilar individuals. Motivated by the public health concern of risky-prescribing among older patients in the United States, we develop network models and tests involving novel network measures to study whether there is evidence of homophily in prescribing and deprescribing in the specific shared-patient network of physicians linked to the US state of Ohio in 2014. Evidence of homophily in risky-prescribing would imply that prescribing behaviors help shape physician networks and would suggest strategies for interventions seeking to reduce risky-prescribing (e.g., strategies to directly reduce risky prescribing might be most effective if applied as group interventions to risky prescribing physicians connected through the network and the connections between these physicians could be targeted by tie dissolution interventions as an indirect way of reducing risky prescribing). Furthermore, if such effects varied depending on the structural features of a physician’s position in the network (e.g., by whether or not they are involved in cliques—groups of actors that are fully connected to each other—such as closed triangles in the case of three actors), this would further strengthen the case for targeting groups of physicians involved in risky prescribing and the network connections between them for interventions. Using accompanying Medicare Part D data, we converted patient longitudinal prescription receipts into novel measures of the intensity of each physician’s risky-prescribing. Exponential random graph models were used to simultaneously estimate the importance of homophily in prescribing and deprescribing in the network beyond the characteristics of physician specialty (or other metadata) and network-derived features. In addition, novel network measures were introduced to allow homophily to be characterized in relation to specific triadic (three-actor) structural configurations in the network with associated non-parametric randomization tests to evaluate their statistical significance in the network against the null hypothesis of no such phenomena. We found physician homophily in prescribing and deprescribing. We also found that physicians exhibited within-triad homophily in risky-prescribing, with the prevalence of homophilic triads significantly higher than expected by chance absent homophily. These results may explain why communities of prescribers emerge and evolve, helping to justify group-level prescriber interventions. The methodology may be applied, adapted or generalized to study homophily and its generalizations on other network and attribute combinations involving analogous shared-patient networks and more generally using other kinds of network data underlying other kinds of social phenomena.

Is organizational performance likely to improve when an organization employs acolytes (i.e., individuals with considerable experience of working with high-reputation industry leaders)? Firms with able, motivated, and opportunity-seeking acolytes are likely to benefit more in terms of unobtrusive access to quality knowledge and improved performance. Through a detailed qualitative treatment, this work identifies high-reputation leaders, acolytes and 312 beauty salons that employed acolytes. An analysis of lagged survey responses of 286 senior managers at these beauty salons showed that the performance of salons improves, when acolytes high in knowledge-sharing competencies–i.e., ability, motivation, and opportunity-seeking–are employed. In line with social learning theory, acolytes acquire and display knowledge-sharing competencies due to their association and work experience with industry greats. This study found that these knowledge-sharing competencies help acolytes overcome the barriers to knowledge-sharing and make knowledge more deployable and redeemable for better performance. We also found that with high homophily between acolytes and fellow employees, knowledge-sharing competencies of acolytes work better and more knowledge is received by the firms.

Based on current research, it is evident that the way people see themselves is shaped by their conversation partners. Historically, this literature focuses on how one individual’s expectations can shape another person’s self-views. Given the reciprocal nature of conversation, we wondered whether conversation partners’ self-views may mutually evolve. Using four-person round-robin conversation networks, we found that participants tended to have more similar self-views post-conversation than pre-conversation, an effect we term “inter-self alignment.” Further, the more two partners’ self-views aligned, the more they enjoyed their conversation and were inclined to interact again. This effect depended on both conversation partners becoming aligned. These findings suggest that the way we see ourselves is coauthored in the act of dialogue and that as shared self-views develop, the desire to continue the conversation increases. [ABSTRACT FROM AUTHOR]

We propose that experiencing a lack of personal control will increase people’s preferences for self-similar others and that this effect would be explained by a greater need for structure. Our hypotheses received support across 11 longitudinal, experimental, and archival studies composed of data from 60 countries (5 preregistered studies, N = 90,216). In an analysis of cross-country archival data, we found that respondents who indicated a lower sense of personal control were less likely to prefer to live with neighbors who had a different religion, race, or spoke a different language (Study 1). Study 2 found that participants who perceived lower (vs. higher) personal control indicated greater liking for coworkers who they perceived to be more self-similar across a wide range of characteristics (e.g., gender, personality). Studies 3a and 3b, two live-interaction experiments conducted in the United States and China, provided additional causal evidence for control-motivated similarity attraction. A causal experimental chain (Studies 4a to 4c) and a manipulation-of-mediation-as-a-moderator study (Study 5) provided evidence for the mediating effects of the need for structure. Study 6, a longitudinal study with Chinese employees, found that workers who reported perceiving a lower (vs. higher) sense of personal control preferred more self-similar coworkers, and this effect was mediated by a greater desire for structure. Finally, exploring downstream consequences, Studies 7a and 7b found that control-motivated similarity attraction was associated with a greater preference for homogenous (vs. diverse) groups. These findings highlight how the fundamental motive for personal control shapes the structure of social life. [ABSTRACT FROM AUTHOR]

The TEST pervasive use of social media has highlighted the importance of developing sophisticated models for early information warning systems within online communities. Despite the advancements that have been made, existing models often fail to adequately consider the pivotal role of network topology and temporal dynamics in information dissemination. This results in suboptimal predictions of content propagation patterns. This study introduces the User Propagation Influence-based Linear Threshold (UPI-LT) model, which represents a novel approach to the simulation of information spread. The UPI-LT model introduces an innovative approach to consider the number of active neighboring nodes, incorporating a time decay factor to account for the evolving influence of information over time. The model's technical innovations include the incorporation of a homophily ratio, which assesses the similarity between users, and a dynamic adjustment of activation thresholds, which reflect a deeper understanding of social influence mechanisms. Empirical results on real-world datasets validate the UPI-LT model's enhanced predictive capabilities for information spread. [ABSTRACT FROM AUTHOR]

AbstractFor statistical analysis of network data, the β -model has emerged as a useful tool, thanks to its flexibility in incorporating nodewise heterogeneity and theoretical tractability. To generalize the β -model, this article proposes the Sparse β -Regression Model (S β RM) that unites two research themes developed recently in modeling homophily and sparsity. In particular, we employ differential heterogeneity that assigns weights only to important nodes and propose penalized likelihood with an l1 penalty for parameter estimation. While our estimation method is closely related to the LASSO method for logistic regression, we develop a new theory emphasizing the use of our model for dealing with a parameter regime that can handle sparse networks usually seen in practice. More interestingly, the resulting inference on the homophily parameter demands no debiasing normally employed in LASSO type estimation. We provide extensive simulation and data analysis to illustrate the use of the model. As a special case of our model, we extend the Erdős-Rényi model by including covariates and develop the associated statistical inference for sparse networks, which may be of independent interest. Supplementary materials for this article are available online, including a standardized description of the materials available for reproducing the work. [ABSTRACT FROM AUTHOR]

This research examines whether categorical closure – an increased tendency for closure in homogeneous triads – matters for tie formation and tie persistence. We utilized 2019–2020 panel data on students' networks at three law schools and employed separable temporal exponential random graph models to examine whether closed triads with shared identities were more likely to form and to persist over time. We also investigated whether closed triads based on shared organizational assignments were associated with lower likelihoods of tie formation and tie persistence over time. Results supported the notion that law students were more likely to form homogeneous closed triads based on shared categories, particularly family background, gender, and race, while closed triads based on organizational assignments were less likely. Closed triads tended to persist over time, but there was some support for the notion that homogeneous closed triads based on family background, college rank, and sexuality were more durable. This study highlights categorical closure as an additional network mechanism giving rise to homogenous groups. • This research examines whether categorical closure – an increased tendency for closure in homogeneous triads – matters for social networks. • This research utilizes longitudinal network data and separable temporal exponential random graph models to test for categorical closure. • Results supported the notion that law students were more likely to form homogeneous closed triads based on some shared categories. • This study highlights categorical closure as an additional network mechanism giving rise to homogenous groups. [ABSTRACT FROM AUTHOR]

Today, with the expansion of online social networks and their impact on various aspects of human life, investigating the interactions between users and identifying influential users for various advertising applications and accelerating or preventing the dissemination of information has been the focus of researchers. One of the fundamental researches is investigating the fact that the similarity of users' characteristics along with their interests leads to new relationships in the friendship network, a concept known as homophily. The study of homophily can provide significant insight into the flow of information and behaviors in a community to analyze the formation of online communities. In recent years, the emergence of location-based social networks (LBSNs) has created massive datasets by sharing spatial and temporal information better than ever before. This issue enables researchers to analyze the behavioral patterns of users and their impact on their social connections and friends. Throughout the present paper, a framework is being defined to examine the effect of combining structural similarity and homophily in determining users' social influence under two scenarios. The experiments simulate performance of nodes on three LBSNs: Gowalla, Foursquare, and Brightkite. By calculating the correlation coefficient for the similarity methods applied, it can be displayed that with the increase in homophily, the correlation of the proposed method and the social influence increases. A new measure of centrality is also introduced by using the topological structure of the user's communication network, such as the eigenvector centrality along with the values of friendship influence and the number of spatial movements of the user. The results show that our proposed centrality matches up to 85% with baseline methods. [ABSTRACT FROM AUTHOR]

Agencies focused on protected areas’ conservation and recreation require internal capacity-building to enhance their organizational resilience (the ability to adapt and persist). Yet, internal capacity-building is often underemphasized as agencies attend to external relationships. This omission can lessen an agency’s ability to adapt to emergent stressors and opportunities. Specifically, relationships within an agency’s groups (i.e., divisions)—the intra-organizational mesoscale between individuals and whole organizations—can increase an agency’s ability to efficiently build resilience-enhancing adaptive capacity. The U.S. National Park Service (NPS) adopted this mesoscale in their Urban Agenda goal of One NPS, or building resilience-enhancing, agency-wide internal relationships. We investigated intra-organizational relationships in this context, examining relationships within (i.e., bonds) and across (i.e., bridges) three NPS groups: parks (physical spaces), programs (community outreach), and offices (administrative functions). Pairing qualitative interviews with quantitative social network analysis in Detroit, Tucson, and Boston, we examined internal relationship prevalence, supports, and opportunities. The NPS has program and office presence in each of these three urban areas but different proximities to national park units, which are the typical face of the NPS. Across these urban areas, we found that the parks group exhibits more bonds (park-to-park relationships), the programs group exhibits more bridges (program-to-park or program-to-office), and the offices group exhibits a mixture of bonds and bridges. To further One NPS and organizational resilience, cultivating bridges among the three groups is key. This investigation may inform a more strategic focusing of an agency’s limited resources. We highlight five directions for protected area managers’ consideration toward this aim: build bridges locally among groups; consider group composition when identifying divisions (i.e., programs appear more heterogeneous or dissimilar from each other than do the park and office groups); reflect on parks’ centrality to NPS identity and relationships; seek organizational structures supportive of relationship development; and focus on the organizational mesoscale for resilience-enhancing adaptive capacity. These directions for strategic focusing of organizational resources are based in the longstanding work of the NPS but ultimately transcend this single agency, providing targeted guidance for protected area agencies in building internal capacity toward external, public-oriented goals. [ABSTRACT FROM AUTHOR]

Background: Peer influence on risky behavior is particularly potent in adolescence and varies by gender. Smoking prevention programs focused on peer-group leaders have shown great promise, and a social influence model has proven effective in understanding adult smoking networks but has not been applied to adolescent vaping until 2023. This work aims to apply a social influence model to analyze vaping by gender in a high school network. Methods: A high school's student body was emailed an online survey asking for gender, age, grade level, vape status, and the names of three friends. Custom Java and MATLAB scripts were written to create a directed graph, compute centrality measures, and perform Fisher's exact tests to compare centrality measures by demographic variables and vape status. Results: Of 192 students in the school, 102 students responded. Students who vape were in closer-knit friend groups than students who do not vape (p <.05). Compared to males who vape, females who vape had more social ties to other students who vape, exhibiting greater homophily (p <.01). Compared to females who do not vape, females who vape were in closer-knit friend groups (p <.05) and had more ties to other students who vape (p <.01). Conclusion: Differences in vaping by social connectedness and gender necessitate school and state policies incorporating the social aspect of vaping in public health initiatives. Large-scale research should determine if trends can be generalized across student bodies, and more granular studies should investigate differences in motivations and social influence by demographic variables to individualize cessation strategies. [ABSTRACT FROM AUTHOR]

This study examines the perspectives of Israeli-Jewish men who are married to Israeli-Arab women. Given religious, ethnic, and political tensions and challenges, romantic relationships between Israeli Jews and Israeli Arabs are not common. The homophilic tendency is a common model used to choose a partner based on religious, social, linguistic and educational similarities. This study utilized interpretive phenomenological analysis approach to focus on a unique and rather rare phenomenon in Israel to understand the lived experiences and coping mechanisms of Jewish men who married Christian or Muslim women in Israel. Fifteen Israeli men married to Arab Muslim or Christian Israeli women were included interviewed. Based on the analysis of the findings, several themes were identified which describe how participants utilize a pragmatic approach to bridge family, social, religious and political tensions. These themes strengthen recent studies, which found a certain degree of flexibility toward homophily among Jews and Arabs in Israel. [ABSTRACT FROM AUTHOR]

The firm-sponsored online brand communities thrive on value-adding interactions. Existing studies, however, ignore the reasons for social interaction. A sufficient understanding of the factors driving social interactions and ultimately affecting community outcomes is still lacking. Our research examines how social interactions occur and influence consumer purchase behavior from a social network perspective, drawing on the theories of planned behavior and homophily. Our exponential random graph (ERG) models show that consumer-specific traits (e.g., deal proneness) and similarity on tenure, location, and deal proneness positively drive social interactions, while similarity on age, premium-product propensity does not. Our two-stage least square (2SLS) regressions find that social interactions among co-located consumers strongly influence purchase behavior. Our study contributes to the social interaction literature by emphasizing the types of social interactions and their antecedents and consequences with various consumer purposes. Our findings open a new research direction and novel business applications in firm-sponsored community management. [ABSTRACT FROM AUTHOR]

We investigate three related problems concerning sampling minorities in attributed networks. This is guided by a general attributed network model which can incorporate several levels of homophily and heterophily, and whose degree and Page-rank distributions have known properties. The first problem investigates sampling schemes that favor the representation of the minority over majority nodes and give preference to "more popular" minority nodes (i.e. higher degree/Page-rank) for a given homophily scenario. We show that (in-)degree and Page-rank sampling schemes increase the probability of sampling a minority node. The second problem concerns the relative ranking of minorities compared to majorities in degree and Page-rank based sampling schemes for several homophily and heterophily scenarios. We provide analytical conditions for the minority nodes to rank higher as a function of the model parameters for the degree based samplings and investigate the problem numerically for Page-rank based sampling schemes. The third problem considers subgraph sampling schemes and the bias of the proportion of minority nodes in top ranked degree nodes in several homophily and heterophily scenarios. Finally, the results and findings obtained from the sampling analysis are assessed on real-world networks. [ABSTRACT FROM AUTHOR]

Graph Convolutional Networks (GCNs) gain remarkable success in graph-related tasks under homophily graph assumption—most connected nodes have the same label. However, this assumption is fragile since heterophily is common in real-world networks, where most linked nodes have different labels. Some methods address heterophily using graph-level weighted combinations of multi-hop neighbor representations. However, they introduce noise and irrelevant information from two aspects: (1) higher-order neighborhoods may include more neighbors with different labels than those with the same label; (2) graph-level weighted combination fails to capture distinct node properties. To address these issues, firstly, a Neighborhood Distribution-induced Similarity (NDS) measure is developed to identify potential similar neighbors for nodes. Secondly, a node-level fusion mechanism Selective-Neighbors Gated Unit (SNGU) is designed to adaptively aggregate potential neighbors, first-hop neighbors, and the node itself by learning distinct weights for nodes. By combining the above two designs, this work proposes a novel Neighbors Selective Graph Convolutional Network (NSGCN), which allows nodes to selectively receive relevant neighbor information for better node representations, effectively modeling homophily and heterophily. Experiments on 10 widely used real-world datasets with varying properties demonstrate the superiority of the NSGCN, surpassing a strong baseline with an absolute increase of 9.83% in classification accuracy. The code is available at https://github.com/GGA23/NSGCN. • We develop a Neighborhood Distribution-induced Similarity measure. • We design a Selective-Neighbors Gated Unit. • We propose a novel Neighbors Selective Graph Convolutional Network. • Better or comparable performance on ten datasets with distinct homophily-heterophily properties. [ABSTRACT FROM AUTHOR]

Influence maximization (IM) is crucial for recommendation systems and social networks. Previous research primarily focused on static networks, neglecting the homophily and dynamics inherent in real-world networks. This has led to inaccurate simulations of information spread and influence propagation between nodes, with traditional IM algorithms’ selected seed node sets failing to adapt to network evolution. To address this issue, this paper proposes a homophilic and dynamic influence maximization strategy based on independent cascade model (HDIM). Specifically, HDIM consists of two components: the seed node selection strategy that accounts for both homophily and dynamics (SSHD), and the independent cascade model based on influence homophily and dynamics (ICIHD). SSHD strictly constrains the proportions of different node types in the seed node set and can flexibly update the seed node set when the network structure changes. ICIHD redefines the propagation probabilities between nodes, adjusting them in response to changes in the network structure. Experimental results demonstrate HDIM’s excellent performance. Specifically, the influence range of HDIM exceeds that of state-of-the-art methods. Furthermore, the proportions of various activated nodes are closer to those in the original network.

Considering the advantages of using AI influencers compared to human influencers, fashion marketers increasingly using AI influencers to promote their products. Hence, continuous research is needed to ensure the effectiveness of AI influencers in promoting fashion products. Through an online survey, 343 valid responses were collected from fashion consumers. The research revealed the importance of perceived homophily and perceived authenticity as the characters of AI influencer. Specifically, perceived homophily promotes the intention to follow AI influencer recommendations as can be explained by the perception of anthropomorphism among social media users. Additionally, the findings reveal that the perception of AI influencer authenticity moderates the relationship between homophily and the intention to follow AI influencer recommendations through anthropomorphism.

The arts and aesthetic experiences have fostered and enhanced relationships between diverse, distinct groups in an effort to build comradery, trust, and engagement. In regards to collaborations between health systems and communities, taking into account strategies to build such relationships is vital in an effort to assure a bidirectional collaboration that implements public health insight and resources effectively. There are many factors warranting consideration when building effective community engagement for health promotion between healthcare systems and local community organizations and residents. Such factors include, but are not limited to, homophily, transitivity, structural holes, and maintaining weak ties. In this brief review, we will explore how the arts can be utilized to broker relationships for healthcare systems implementing community engagement with partnering, diverse social networks. Specifically, we will explore the role of the arts and aesthetic experience to create homophily, foster transitivity and balance, enhance collaboration and build meaningful connections between healthcare systems and social networks to more effectively address health concerns for all involved.