Stochastic Actor-oriented Models Research Articles

The cycle of violence: effects of violence experience, behavior, and attitudes on adolescents’ peer rejection networks

Previous research on adolescent peer networks has mainly focused on friendship networks and their association with violence, but very limited research is available on peer rejection networks. This lack of knowledge hinders the effectiveness of preventing peer rejection and its negative effects. Based on the theory of the cycle of violence, the present study examines the extent to which parental physical abuse experiences, aggressive behavior toward peers and acceptance of violence are related to peer rejection networks at school. Social network analysis with a stochastic actor-oriented model of longitudinal data collected from high school students (Wave 1, n = 620; Wave 2, n = 590) confirms that adolescents who frequently use aggression toward their peers are more likely to be rejected, especially if those adolescents have experienced abuse. Similarly, peers are more likely to reject adolescents with high levels of accepting violence. The results also show that aggression toward peers generally tends to decrease over time but not for adolescents who reject a larger number of students. For students who reject many peers, aggression frequency increases. From the perspective of resilience theory, peer rejection, when combined with aggression toward peers and acceptance of violence, particularly in female adolescents, creates a significant risk factor for socio-emotional development. Therefore, tackling violence attitudes, experiences and behavior in the school environment and at home is crucial in overcoming the cycle of violence.

Examining the social and behavioral dynamics of substance use in a longitudinal network study in rural Appalachia

BackgroundPrior studies have shown that individuals and their peers often have similar substance use behaviors, but the mechanisms driving these similarities – particularly in rural settings, are not well understood. The primary objectives of this analysis are to (1) identify factors that contribute to relationship turnover and maintenance within a rural network of persons who use drugs (PWUD), (2) determine whether assimilation and/or homophily shape participants use of injection drugs, heroin, and stimulants (methamphetamine and cocaine), and (3) assess the extent that these mechanisms influence networks ties and/or behaviors and whether these effects vary across time. MethodsSociometric network data were collected from a cohort of PWUD in rural Eastern Kentucky at baseline (2008–2010) and at four follow-up visits conducted approximately semiannually. Stochastic actor-oriented models (SAOMS) were used to model network structure and participant behaviors as jointly dependent variables and to identify characteristics associated with the maintenance, dissolution, and formation of network ties and changes in drug use behaviors. ResultsFindings suggest (1) greater network stability over time for reciprocal and transitive relationships, (2) both homophily and assimilation played a greater role in shaping injection drug use (IDU) initiation and cessation than they did in shaping heroin and stimulant use, and (3) the importance of these mechanisms appeared consistent over time. ConclusionGiven the stability of particular network structures and evidence of both homophily and assimilation with respect to drug-use behaviors, interventions that leverage social networks could be used to motivate health-promoting behaviors.

Evolution of Project-Based Collaborative Networks for Implementing Prefabricated Construction Technology: Case Study in Shanghai

Prefabricated construction (PC) is considered to be a low-carbon construction method. Implementing prefabricated construction projects (PCPs) requires multiple industry organizations to participate and collaborate. As different PCPs are initiated and implemented, industry organizations will gradually gather into a complex and evolving collaborative network at the industry level based on specific collaboration relationships with different project backgrounds. The evolution of the collaborative network is related to how industry organizations interact with each other, and how PC-related knowledge and innovation has spread among organizations in the long term. However, the laws of network evolution and the micro effects that drive network evolution are still unknown. This study analyzes 236 prefabricated construction projects (PCPs) in Shanghai during 2015–2023, using the stochastic actor-oriented models (SAOM) method to explore how the macro structure of project-based inter-organizational collaborative networks for prefabricated construction (PC) technology implementation evolves over time, and how micro effects jointly support the evolution of the networks. The macro-level descriptive analysis of the network indicates that the collaborative network has become increasingly dense over time and continues to show a core–peripheral structure, with a small number of super-connected organizations. The micro-level SAOM analysis further reveals that the evolution of the collaborative network structure is driven by structure-based preferential attachment and geographic proximity effects, as well as attribute-based ownership similarity effect. This exploratory effort applies a network dynamics model to investigate the micro mechanism of the evolution of inter-organizational collaboration. The research results provide theoretical guidance and decision-making references for PC industry organizations to develop efficient network action strategies. In addition, it can help industry managers to formulate appropriate network management strategies.

Unpacking the network dynamics of online political discussions: Stochastic actor-oriented modeling with political/sociopsychological/linguistic factors

The underlying mechanisms of online political discussions which may involve power dynamics have seldom been explored through a dynamic network approach, even though discussions themselves are inherently relational and dynamic processes. It remains unclear how discussions are shaped over time between egos/alters with different political/sociopsychological/linguistic attributes as well as by the existing discussion ties surrounding them. Based on a stochastic actor-oriented modeling constructed from pre-survey/virtual discussion/post-survey data, we found some evidence that, in the politically heterogeneous context, shared political ideology, alter’s political tolerance level, and the extent of negative/strong/assertive language used by alter are associated with the likelihood of discussion tie creation/maintenance. In the homogeneous context, the extent to which ego perceives alter as politically knowledgeable and personally likable was clearly associated with ego’s tendency to create or maintain discussion ties with alter over time. This study uncovers alter/dyad-centered variables that are critical, but have been overlooked, for communication research.

Swimming against the Tide: A Mixed-Methods Study of how the MARKERS Educator Wellbeing Program Changed Educators’ Relational Space

AbstractEffective educator wellbeing interventions should consider the individual, relational, and contextual influences on educator wellbeing. Given the gap between the effectiveness of positive psychology interventions (PPIs) and their real-world success, it is essential to understand and adapt to the school context when integrating psychological interventions into educational settings. The MARKERS (Multiple Action Responsive Kit for Educator, Relational, and School wellbeing) educator wellbeing program is multi-level, designed to consider the individual, relational, and contextual influences on wellbeing. Its multi-foci design also allowed for adaptations to specific contexts. This study examines the impact of the MARKERS program in one school in Aotearoa New Zealand. We use a mixed methods case study approach that draws on measures of educator wellbeing, social network measures of energising interactions, and focus group data. The use of stochastic actor-oriented models (SAOMs) allowed us to examine changes to the social network over time. Findings show that MARKERS program participants experienced a significant positive change in their relational space and experienced more energising interactions, but they were ‘swimming against the tide’ as other staff in the school had fewer energising interactions with their colleagues. Our study illustrates the importance of considering the relational and contextual influences on wellbeing when evaluating educator wellbeing interventions.

Exploring the Effects of Multi-Governance Mechanisms throughout the Dynamic Evolution of the Cooperative Innovation Network

The sustainable evolution of cooperative innovation networks is determined to a great extent by the effectiveness of their governance mechanisms. In this study, we draw from social network and stakeholder theories to emphasize two types of mechanisms that coordinate cooperative innovation: the internal drivers of transitivity and status, which are endogenous mechanisms of network embeddedness, and the external drivers of association autonomy, industrial policy support, and institutional environment establishment, which are the governing effects of external stakeholders. We constructed cooperative innovation networks using a dataset on joint applications for patents in China’s electronics information industry during 2006–2018 and applied a Stochastic Actor-Oriented Model (SAOM) for analytical purposes. The findings show that as networks evolve, the effect of transitivity on cooperative innovation first slightly decreases and then intensifies. The influence of status and industrial policy support intensifies first and then weakens. The impact of association autonomy remains stable, and institutional environment establishment on cooperative innovation intensifies. We also provide theoretical and managerial implications for the dynamic evolution of cooperative innovation networks.

Assessing Drivers of Sustained Engagement in Collaborative Governance Arrangements

Abstract The formal engagement of diverse stakeholder groups in policy design and implementation has become a mainstay governance strategy. While much has been learned about collaborative governance arrangements in terms of their structure, processes, and participant dynamics, one particularly salient dynamic has been relatively underexplored: the factors contributing to sustained participation in collaborative venues. Public administration and policy have developed a variety of conceptual theories which draw attention to interpersonal interactions and the ability of stakeholders to garner political wins as important contributing factors to sustained participation. In this paper, we test four theoretically rooted hypotheses to investigate stakeholder attendance in the collaborative governance case of an environmental justice council. We analyze council meeting minute data using computational text analysis tools and a Stochastic Actor-Oriented Model to assess: (i) conflict and concord, measured in terms of repeated (dis)agreement with others; and (ii) interest advancement, or the extent to which a stakeholder makes positive, neutral, and negative comments towards topics which become the council’s annual objectives in relation to an individual’s attendance. Our interpersonal interaction results show increased positive relationships are associated with increased attendance, and increased negative relationships are associated with decreased attendance, but, for both cases, only when interactions are repeated and not one-off. Our interest advancement results show: (1) an increase in supported annual objectives is associated with decreases in attendance for an individual stakeholder, but (2) increased oppositional and neutral annual topics are associated with a greater likelihood of attendance. This paper contributes to existing scholarship on collaborative governance by offering additional insights into individual factors associated with sustained engagement in the collaborative venue. Furthermore, the paper offers a generalizable methodological approach for analyzing these dynamics drawing on computational text analysis of meeting minute data.

Dynamic social network analysis of a brief alcohol intervention trial in heavy-drinking college students shows spillover effects.

Heavy-drinking college students tend to have close social networks, and there is theoretical and empirical support for the idea that behavior change can spread through those networks via close ties. The objective of this research was to determine whether intervention-induced behavior change in a subset of heavy drinkers in a sociometric (whole) college class-year social network is transmitted to other heavy drinkers in the network, resulting in reduced behavioral risk and change in network ties. We conducted a controlled trial in which most of a first-year college class (N = 1236; 56.9% female) was enrolled, with alcohol use and social network ties measured early in each of three semesters. Following a baseline assessment, the network was divided into two groups, brief motivational intervention (BMI) and natural history control (NHC) according to dormitory residence location. A subset of heavy drinkers in each group was selected, and those in the BMI group received an in-person intervention. Using stochastic actor-oriented modeling, we found a significant tendency for participants in the BMI group to shed ties with individuals with similar drinking behaviors between the first and second semesters, relative to the NHC group. Furthermore, heavy drinkers with reciprocal ties to intervention recipients in the BMI group showed a significant reduction in drinks per week. Individual alcohol interventions appear to have effects both on behavior and network connections among individuals who did not receive the intervention. Continued research is needed to identify the optimal conditions for the diffusion of behavior change.

Re-print of: Contextualizing oppositional cultures: A multilevel network analysis of status orders in schools

Different lines of research have argued that specific groups, such as boys or ethnic minorities, are more prone to develop an anti-school culture than others, leading to group differences in the social acceptance of high performers. Taking an ecological view, we ask to what extent the school context promotes or prevents the emergence of group-specific oppositional cultures. Theoretically, we argue that group-based oppositional cultures become more likely in schools with low socio-economic resources and in schools where socio-economic differences align with demographic attributes. We test our hypotheses based on data from a large-scale, four-wave network panel survey among more than 4000 students in Germany. Applying stochastic actor-oriented models for the coevolution of networks and behavior, we find that group-based oppositional cultures in which students like high performers less are very rare. However, in line with theoretical expectations, the less resourceful a school is, the more boys tend to evaluate high-performing peers less positively than girls do. Moreover, the more ethnic minority boys are socioeconomically disdvantaged in a school, the more they tend to evaluate high performers less positively than majority boys do.

Co-evolution of a socio-cognitive scientific network: A case study of citation dynamics among astronomers

This paper aims to understand how a group of academics cite each others’ work through time, considering the simultaneous co-evolution of three networks representing their scientific collaboration, the journals in which they publish and institutional membership. It argues that both social and cognitive processes contribute to these dynamics. Two types of network mechanisms are considered specifically: closures by affiliation and closures by association. To assess whether these mechanisms generate the macro features of the network under study, we propose new features for three-mode multilevel networks such as the mixed geodesic distances, mixed degree distributions, and the mixed quadrilateral census. We investigate whether a micro-level model that considers the above-mentioned network mechanisms is able to correctly reproduce these features. We apply stochastic actor-oriented models (SAOMs) for one-mode and two-mode networks to link the micro-macro processes using a dataset of a scientific community of astronomers from 2013 to 2015. The results suggest that social relationships grounded on scientific collaboration and proximity based on institutional affiliation are more accurately suited to understanding the co-evolution of the network of citations than an alternative approach that merely considers cognitive-based networks measured as the similarity in publishing in the same journals.

Adolescents’ Drinking Behavior Off- and Online: Disentangling Exposure Effects and Selective Exposure in Networked Communication Structures

This article applies a network approach to better understand the often-demonstrated link between adolescents’ drinking behavior and their exposure to alcohol-related content on social media. Focusing on social dynamics among adolescents and their peers, we investigate the causes and consequences of exposure to individual peers who share alcohol-related content online. Drawing on social network literature and the perspective of networked communication online, we distinguish between exposure effects and selective exposure as the two core dynamics that can explain the association between drinking behavior and exposure to alcohol-related content online. Based on a two-wave network survey among adolescents aged 14 to 17 (n = 277), we applied a longitudinal network analysis to test both dynamics simultaneously. The findings indicate no exposure effects but robust evidence for selective exposure. This means that drinking adolescents are more likely to become exposed to peers who post alcohol-related content. The stochastic actor-oriented model hereby controls for rivaling explanations, such as the tendency to be exposed to friends, classmates, and peers of the same gender. In addition to these empirical findings, we discuss the value of the network approach, outlining the implications for future research and prevention strategies.

Who will participate in online collaborative problem solving? A longitudinal network analysis

ABSTRACT Community-based courses, driven by connectivist learning theory, provide learners with a social environment that supports collaborative problem solving (CPS). The purpose of this study is to investigate the characteristics of potential collaborators before they engage in CPS. This study analyzed a community-based course, a cMOOC with a total of 145 learners participated in the thematic learning stage and 52 of the 145 chose to participate in the CPS. The interaction pattern of the collaborators and the indirect effects of individual attribute-based (exogenous) effects and network structure-based (endogenous) effects on the interaction pattern were examined using the quadratic assignment procedure (QAP) and the stochastic actor-oriented model (SAOM). Results suggest that substantial interaction activeness and interaction attractiveness are key patterns of the collaborators’ social interactions before CPS, and there is some interaction homogeneity among the collaborators. Some individual attribute-based effects, such as age, gender, and occupation, will reduce the early interaction attractiveness of the collaborators. The reciprocity, transitivity, and cumulative advantages of the network structure-based effects will gradually increase collaborators’ interaction attractiveness; in contrast, the network structure-based effects simultaneously limit collaborators’ interaction activeness. This study provides a theoretical foundation and practical experience regarding encouraging learners’ deep collaboration in community-based courses.

How does socioeconomic homophily emerge? Testing for the contribution of different processes to socioeconomic segregation in adolescent friendships

Homophily – the fact that friendships happen at a higher rate among similar individuals – does not necessarily imply homophilic selection – the tendency to look for similar friends. This is particularly true for socioeconomic homophily: because individuals’ social class impacts most aspects of their lives, there are several ways in which it can favor homogeneity in friendship networks. Applying this view to the relationships of French middle-school students, the present article tries to unravel the contribution of various relational processes to the emergence of socioeconomic homophily. Stochastic Actor-Oriented Models, a class of generative models designed for network panel data, are applied to the friendship networks of 820 students surveyed over a year and a half. Simulations derived from the estimated models are then used to assess the impact of different processes on aggregated levels of homophily. To that aim, a new metric is proposed that help researchers decompose an observed property of a network into a set of contributions from low-order processes, called “contribution scores”. Results suggest that direct homophilic selection can be important in explaining socioeconomic homophily, but not in all cases. Indirect inducers, such as residential propinquity or ethnic selection, also play a significant role. Moreover, endogenous network processes – namely reciprocation and transitive closure – strongly contribute to homophily by reinforcing other homophily-inducing processes.

Status, cognitive overload, and incomplete information in advice-seeking networks: An agent-based model

Advice-seeking typically occurs across organizational boundaries through informal connections. By using Stochastic Actor-Oriented Models (SAOM), previous research has tried to identify the micro-level mechanisms behind these informal connections. Unfortunately, these models assume perfect network information, require agents to perform too cognitively demanding decisions, and do not account for threshold-based critical events, such as simultaneous tie changes. In the context of knowledge-intensive organizations, the shortage of high-skilled professionals could determine complex network effects given that many less-skilled professionals would seek advice from a few easily overloaded, selective high-skilled, who are also sensitive to status demotion. To capture these context-specific organizational features, we have elaborated on SAOM with an agent-based model that assumes local information, status-based tie selection, and simultaneous re-direction of multiple ties. By fitting our simulated networks to Lazega’s advice network used in previous research, we reproduced the same set of macro-level network metrics with a parsimonious model based on more empirically plausible assumptions than previous research. Our findings show the advantage of exploring multiple generative paths of network formation with different models.

What drives network evolution? Comparing R&D project and patent networks in the EU

Abstract Collaboration networks are the main mechanisms through which regional innovation capacities are enhanced. These networks have been analyzed by using data either on research projects or patents. However, analyzing only one type of network can limit our understanding of regional innovation dynamics. In this paper, we investigate the drivers of network evolution in two inter-regional network types within the European Union: R&D project networks and co-patenting networks. Specifically, we examine data on Framework Program project collaborations and patent collaborations at the NUTS2 regional level between 2011 and 2019. Our empirical strategy is based on Stochastic Actor-Oriented Model where we analyze and compare the factors that affect the evolution of two networks. We find that path-dependent processes resulting from past networks, such as triadic closure, preferential attachment, and tie repetition, play a more important role in explaining the evolution of R&D project networks compared with patent networks. On the other hand, regional characteristics, particularly the patenting intensity of a region and similarity in patenting between regions appear to be more influential in shaping patent networks. These results have important implications for the future evolution of knowledge networks in Europe.

Adolescent friendship, cross-sexuality ties, and attitudes toward sexual minorities: A social network approach to intergroup contact

Social ties between members of in- and outgroups are theorized to reduce individual levels of prejudice. However, instances of intergroup contact are not isolated events; cross-group interactions are embedded in broader networks defined by various social processes that guide the formation and maintenance of interpersonal relationships. This project reconsiders the potential benefits of intergroup contact by applying a network perspective to examine whether friendships between youth of different sexualities can shape individuals’ homophobic attitudes. The impact of cross-sexuality ties is evaluated through the application of stochastic actor-oriented models (SAOMs) to a two-wave sample of Dutch adolescents. Results indicate that the benefits of cross-sexuality connections become negligible when we account for how patterns of network connectivity and segregation are informed by other individual-level traits, such as age, religious background, ethnicity, and gender. In other words, heterosexual adolescents who are situated in network positions that provide opportunities to form cross-sexuality friendships would be expected to report less homophobic attitudes even in the absence of this intergroup contact. These findings suggest that the cross-sexuality contact observed in the social world often represents instances of “preaching to the choir,” limiting the potential for intergroup connections to challenge systems of social inequality.

Network patterns of university-industry collaboration: A case study of the chemical sciences in Australia

University–industry (U–I) collaboration takes on many forms, from research services, teaching and training, to curiosity-led research. In the chemical industries, academic chemists generate new knowledge, address novel problems faced by industry, and train the future workforce in cutting-edge methods. In this study, we examine the dynamic structures of collaborative research contracts and grants between academic and industry partners over a 5-year period within a research-intensive Australian university. We reconstruct internal contract data provided by a university research office as records of its collaborations into a complex relational database that links researchers to research projects. We then structure this complex relational data as a two-mode network of researcher-project collaborations for utilisation with Social Network Analysis (SNA)—a relational methodology ideally suited to relational data. Specifically, we use a stochastic actor-oriented model (SAOM), a statistical network model for longitudinal two-mode network data. Although the dataset is complicated, we manage to replicate it exactly using a very parsimonious and relatable network model. Results indicate that as academics gain experience, they become more involved in direct research contracts with industry, and in research projects more generally. Further, more senior academics are involved in projects involving both industry partners and other academic partners of any level. While more experienced academics are also less likely to repeat collaborations with the same colleagues, there is a more general tendency in these collaborations, regardless of academic seniority or industry engagement, for prior collaborations to predict future collaborations. We discuss implications for industry and academics.

Continuous time graph processes with known ERGM equilibria: contextual review, extensions, and synthesis

ABSTRACT Graph processes that unfold in continuous time are of obvious theoretical and practical interest. Particularly useful are those whose long-term behavior converges to a graph distribution of known form. Here, we review some of the conditions for such convergence, and provide examples of novel and/or known processes that do so. These include subfamilies of the well-known stochastic actor-oriented models, as well as continuum extensions of temporal and separable temporal exponential family random graph models. We also comment on some related threads in the broader work on network dynamics, which provide additional context for the continuous time case.

The role of selection in socioeconomic homophily: Evidence from an adolescent summer camp

Socioeconomic homophily in friendship networks is the result of several co-occurring processes, which are extremely challenging to disentangle. We propose to study the particular context of a three-week summer camp in France that gathered teenagers from varied socioeconomic backgrounds. We argue that this camp provides a unique opportunity to observe the sociability of adolescents in well-bounded settings with equalized meeting opportunities, thus helping us to narrow down the specific role of homophilic selection - the process by which individuals actively select similar friends. We use Stochastic Actor-Oriented Models to analyze the declared friendships of participants. Furthermore, we introduce a novel longitudinal extension of the Exponential Random Partition Model (ERPM), a model developed for relational data organized in discrete groups, which we apply to observed meal-sharing among adolescents. Results point to weak to non-existent homophilic selection during the stay. In turn, this suggests that structural opportunities and contextual moderators might be essential in explaining the amount of socioeconomic homophily found at school or in other contexts.

School Transitions, Peer Processes, and Delinquency: A Social Network Approach to Turning Points in Adolescence

Objectives: We examine how normative school transitions (e.g., moves from elementary to middle school) shape adolescents’ experiences with three network processes that inform delinquency: delinquent popularity, delinquent sociability, and friend selection on shared delinquency participation. Methods: By applying stochastic actor-oriented models to a sample of panel data on 13,752 students from 26 school districts in the PROSPER study, we compare outcomes for students who change schools between 6th and 7th grade to those who remain in the same building. Results: We find that adolescents who transition schools between these grades have significantly different experiences with delinquency-related network processes when compared to their peers who do not make this change. For instance, in schools that merge students from multiple elementary schools to a single middle school, delinquent youth experience a reduction in their popularity and sociability following the school transition. These declines do not characterize the social experiences of delinquent adolescents who do not change schools during this period. Conclusions: Our findings suggest that school districts can organize transition patterns to provide youth a chance to sever harmful connections, start anew, and reduce their participation in delinquency.