Search

This article demonstrates our methodology for studying the process of intra-Catholic confessional affiliation during the schism that occurred in the Catholic Church in the eighteenth-century Dutch Republic. The schism resulted in the remarkable fact that the Republic, a Protestant state, became home to two competing Catholic Churches, the Roman Catholic Church and the Roomsch-Katholieke Kerk der Oud-Bisschoppelijke Cleresie (​​OBC Church). In order to understand the choices made by laypeople for one of the two Catholic Churches, we created a dataset based on the baptisms and marriages taking place in two mission stations that were part of the OBC Church in the cities of Utrecht and Leiden. The data was ingested into a specifically designed graph database – connecting people, events (baptism and marriages), and places (churches and secular courts) – that enabled us to study the people who participated in events in the Catholic Churches as well as their roles at these events. In addition, we constructed two-mode networks, connecting people to events, and their projections, consisting only of links between people. Taken together, this approach allowed us to perform both detailed and structural analysis of the data. One insight revealed by our analysis is the existence of a group of lay Catholics who participated in events taking place in rival Catholic Churches. Moreover, network analysis has shown that the process of intra-confessional religious affiliation did not take place in the context of larger groups or collectives, but nor was it a strictly individual affair, as it mainly occurred at the level of couples or individual family nuclei. Our mixed-methods approach, combining qualitative and quantitative analyses, has various advantages as it (1) enhances our understanding of the schism; (2) enables a more detailed analysis of religious choice than the quantitative methodology adopted in the older literature on the schism; and (3) spurs and gives focus to further archival research.

Feld's focus theory is one of the most influential approaches in social network analysis. However, with very few exceptions, empirical assessments of the theory have only focused on a narrow range of its predictions premised on comparative statics. This paper restates classical focus theory in terms of dependence between multiple network layers as they co-evolve, yielding dynamic focus theory. Social foci serve as an ecology within which person-to-person relations form and as a mechanism via which tastes and behaviors diffuse within a population through interpersonal ties. We argue this is a type of "focus effect" distinct from the standard tie-generation process typically considered. In addition, we go beyond previous single-foci studies in considering multiple foci types, allowing us to ascertain which foci—e.g., clubs, activities, musical genres, or academic course areas—act more like tie generators or which ones as taste diffusers. Using rich data from the NetSense and NetHealth studies, we use recently developed Stochastic Actor-Oriented Models (SAOMs) for two-mode networks to estimate simultaneous foci effects across different foci types. We find that musical genres function primarily as taste-diffusers, club types exclusively as tie generators, and course areas and activities as both tie generators and taste diffusers. We conclude by discussing key implications of dynamic focus theory, including how foci properties can account for variability in foci effects and the role different types of social foci play in social influence and the diffusion of tastes and behaviors. • Building on classical focus theory, we develop a dynamic focus theory. • Dynamic focus theory links the co-evolution of multiple networks to diffusion processes. • We find some foci function primarily as tie generators, increasing the probability that two people form a social tie. • We find other foci act more like diffusion points, amplifying the dyadic social influence processes. [ABSTRACT FROM AUTHOR]

The recent popularity of models that capture the dynamic coevolution of both network structure and behavior has driven the need for summary indices to assess the adequacy of these models to reproduce dynamic properties of scientific or practical importance. Whereas there are several existing indices for assessing the ability of the model to reproduce network structure over time, to date there are few indices for assessing the ability of the model to reproduce individuals’ behavior patterns. Drawing on the widely used strategy of assessing model adequacy by comparing index values summarizing features of the observed data to the distribution of those index values on simulated data from the fitted model, we propose four goals that a researcher could reasonably expect of a joint structure/behavior model regarding how well it captures behavior and describe indices for assessing each of these. These reasonably simple and easily implemented indices can be used for assessing model adequacy with any dynamic network models jointly working with networks and behavior, including the stochastic actor-based models implemented within software packages such as RSien version 1.2-24. We demonstrate the use of our indices with an empirical example to show how they can be employed in practical settings, with an additional extension to modeling affiliation dynamics in two-mode networks. Key scripts are provided in the Supplemental Document (which can be found at http://smr.sagepub.com/supplemental/).

In a previous paper, Kovacs (2010) proposed a generalized relational similarity measure based on iterated correlations of entities in a network calibrated by their relational similarity to other entities. Here I show that, in the case of two-mode network data, Kovacs's approach can be simplified and generalized similarities calculated non-iteratively. The basic idea is to rely on initial similarities calculated from transforming the two-mode data into one-mode projections using the familiar duality approach due to Breiger (1974). I refer to this as two-mode relational similarities and show, using the Southern Women's data and data from Senate voting in the 112th U.S. Congress, that it yields results substantively indistinguishable from Kovacs's iterative strategy. • Previous work introduced two-mode similarity measures using iterated correlations. • This paper proposes non-iterative measures of two-mode similarity using projections. • The two-mode relational similarity performs as well as the iterative approach. [ABSTRACT FROM AUTHOR]

The recent popularity of models that capture the dynamic coevolution of both network structure and behavior has driven the need for summary indices to assess the adequacy of these models to reproduce dynamic properties of scientific or practical importance. Whereas there are several existing indices for assessing the ability of the model to reproduce network structure over time, to date there are few indices for assessing the ability of the model to reproduce individuals’ behavior patterns. Drawing on the widely used strategy of assessing model adequacy by comparing index values summarizing features of the observed data to the distribution of those index values on simulated data from the fitted model, we propose four goals that a researcher could reasonably expect of a joint structure/behavior model regarding how well it captures behavior and describe indices for assessing each of these. These reasonably simple and easily implemented indices can be used for assessing model adequacy with any dynamic network models jointly working with networks and behavior, including the stochastic actor-based models implemented within software packages such as RSien version 1.2-24. We demonstrate the use of our indices with an empirical example to show how they can be employed in practical settings, with an additional extension to modeling affiliation dynamics in two-mode networks. Key scripts are provided in the Supplemental Document (which can be found at http://smr.sagepub.com/supplemental/).

Social networks of socially disadvantaged individuals can help them in coping with everyday life and avoiding social exclusion. At the same time, social ties also have the power to bind an individual to their disadvantageous situation, perpetuating the risks of social exclusion. One mechanism through which ties can be established are “foci”: extra‐network structures around which common interactions occur (e.g., family, workplace, clubs) that usually have spatial anchor points (places) where joint interactions happen. To better understand this interplay of places and networks, we use a methodological novelty that connects a person’s everyday places with their ego‐centred network (two‐mode network). We analyse in depth two cases (elderly women living alone) from a mixed‐methods study conducted in rural peripheries in eastern Germany, and we combine data from GPS tracking, qualitative interviews, and egocentric networks. A central finding of our analysis is that tie formation in places is more successful if ego has certain resources (e.g., cultural, financial, or time resources) that allow them to utilise places as foci—hence, ego and places must “match” in their characteristics. Beyond that, the existing foci (and their spatial anchoring as places in everyday life) in which ego is integrated must be considered as structures. Even if a person has enough resources and easy access to places with characteristics that promote contact, this does not automatically mean that they will form ties in such places, as the person’s network plays a major role in whether they frequent these places and establish new ties there.

This study aims to examine the relationship between job-seeking behaviors and the employment rates and employment status of persons with disabilities (PWDs) by applying the social network method. It seeks to predict employment outcomes based on the structural characteristics and number of job-seeking behaviors. The study conducted an analysis of 1,697 PWDs who participated in one or more job-seeking activities by using data from the 2017 Korea Employment Panel Survey for Persons with Disabilities. Two-mode network data, with one set of actors representing individuals and another set of data consisting of 16 job search activities, were analyzed. The employment rate of PWDs increased as the number of core job search behaviors increased. The results of research suggest that vocational rehabilitation professionals should consider the structural aspects of job-seeking behavior and the patterns of relationships among PWDs rather than treating each job-seeking behavior as an independent predictor of employment for PWDs in order to promote their employment. This finding highlights the importance of considering the interrelatedness of job-seeking behaviors among PWDs for effective vocational rehabilitation. [ABSTRACT FROM AUTHOR]

The New Education movement was a remarkable coalition of national reform movements that emerged at the turn of the twentieth century. As a heterogeneous movement that was united only in its opposition to the schooling system at the time, its structure and boundaries in the UK have remained a matter of academic debate. This article implements the previously proposed idea of treating New Education as a social movement and analysing the networks between reformers. A social network analysis of the central 58 reformers suggests that the movement was initially divided into two ideologically separate subgroups, but that from ca. 1905 onwards the reformers were strongly interconnected despite their different interests. Thus, by focusing on the social structure of the movement's core rather than its educational thought, the article challenges the assumption that the New Education movement was fragmented and characterised by tensions. It also furthers the discussion on the feasibility of social network analysis for studying educational reforms. [ABSTRACT FROM AUTHOR]

Social networks of socially disadvantaged individuals can help them in coping with everyday life and avoiding social exclu‐ sion. At the same time, social ties also have the power to bind an individual to their disadvantageous situation, perpetuating the risks of social exclusion. One mechanism through which ties can be established are “foci”: extra‐network structures around which common interactions occur (e.g., family, workplace, clubs) that usually have spatial anchor points (places) where joint interactions happen. To better understand this interplay of places and networks, we use a methodological nov‐ elty that connects a person’s everyday places with their ego‐centred network (two‐mode network). We analyse in depth two cases (elderly women living alone) from a mixed‐methods study conducted in rural peripheries in eastern Germany, and we combine data from GPS tracking, qualitative interviews, and egocentric networks. A central finding of our analysis is that tie formation in places is more successful if ego has certain resources (e.g., cultural, financial, or time resources) that allow them to utilise places as foci—hence, ego and places must “match” in their characteristics. Beyond that, the existing foci (and their spatial anchoring as places in everyday life) in which ego is integrated must be considered as structures. Even if a person has enough resources and easy access to places with characteristics that promote contact, this does not automatically mean that they will form ties in such places, as the person’s network plays a major role in whether they frequent these places and establish new ties there. [ABSTRACT FROM AUTHOR]

Identifying important actors (or nodes) in a two-mode network is a crucial challenge in mining, analyzing, and interpreting real-world networks. While traditional bipartite centrality indices are often used to recognize key nodes that influence the network information flow, inaccurate results are frequently obtained in intricate situations such as massive networks with complex local structures or a lack of complete knowledge about the network topology and certain properties. In this paper, we introduce Bi-face (BF), a new bipartite centrality measurement for identifying important nodes in two-mode networks. Using the powerful mathematical formalism of Formal Concept Analysis, the BF measure exploits the faces of concept intents to detect nodes that have influential bicliques connectivity and are not located in irrelevant bridges. Unlike off-the shelf centrality indices, it quantifies how a node has a cohesive substructure influence on its neighbour nodes via bicliques while not being in network core-peripheral ones through its absence from non-influential bridges. In terms of identifying accurate node centrality, our experiments on a variety of real-world and synthetic networks show that BF outperforms several state-of-the art bipartite centrality measures, producing the most accurate Kendall coefficient. It provides unique node identification based on network topology. The findings also demonstrate that the presence of terminal nodes, influential bridges, and overlapping key bicliques impacts both the performance and behaviour of BF as well as its relationship with other traditional centrality measures. On the datasets tested, the computation of BF is at least twenty-three times faster than betweenness, eleven times faster than percolation, nine times faster than eigenvector, and ten times faster than closeness.

This article studies national-ethnic images and cultural distances utilizing contemporary network methodology. The conceptual framework related to cognitive maps of perceived in-group and out-group stereotypes builds on an extended application of the catnet concept introduced by Harrison White. Employing an adapted version of the classical comparative approach by Buchanan and Cantril, the survey took place online in 2016/17, in a joint project with Greek and Hungarian samples. The analyses build on a two-mode network approach of attributes attached to these two, and four other nationalities, highlighting emotional and competence dimensions and skills/knowledge styles in an attribute/nation perspective. The impact of recent crises is also treated by contrasting the cognitive maps of various segments of the Greek and Hungarian populations. [ABSTRACT FROM AUTHOR]

Multi-location knowledge-intensive firms span their value chains and thus their locations across space. Increased globalization alters the spatial configuration of such networks of knowledge creation. Longitudinal social network analysis allows detecting temporal changes in the arrangement of nodes and edges in the network and resulting changes in the overall structure. We use this approach to study for Germany the spatio-temporal dynamics of knowledgeintensive services firms - advanced producer services (APS) - in the years between 2009 and 2019. Multi-location APS firms are considered as vanguard of spatial structural change and thus lending to study their location choice behavior. A common approach is to analyze a onemode intercity network where cities are the nodes. We take a different approach and include the firms' perspectives. We work directly with the original data structure of a two-mode network including cities and firms as two node sets and we apply stochastic actor-oriented models for network dynamics. Results show that the spatio-temporal dynamics are characterized by both agglomeration and network economies. On a local scale, APS firms continue their location expansion over time and concentrate in agglomerations where many other APS firms and a greater availability of workforce are present. Simultaneously, they also choose new locations in agglomerations further apart from their present locations. On a supralocal scale, the network grows denser over time. Agglomerations that are attractive for APS firms in 2009 become even more attractive in 2019. Our analysis contributes to an understanding of how interactions amongst cities and firms on a local scale give rise to the empirically observed network patterns on a supra-local scale. [ABSTRACT FROM AUTHOR]

Multi-location knowledge-intensive firms span their value chains and thus their locations across space. Increased globalization alters the spatial configuration of such networks of knowledge creation. Longitudinal social network analysis allows detecting temporal changes in the arrangement of nodes and edges in the network and resulting changes in the overall structure. We use this approach to study for Germany the spatio-temporal dynamics of knowledge-intensive services firms – advanced producer services (APS) – in the years between 2009 and 2019. Multi-location APS firms are considered as vanguard of spatial structural change and thus lending to study their location choice behavior. A common approach is to analyze a one-mode intercity network where cities are the nodes. We take a different approach and include the firms’ perspectives. We work directly with the original data structure of a two-mode network including cities and firms as two node sets and we apply stochastic actor-oriented models for network dynamics. Results show that the spatio-temporal dynamics are characterized by both agglomeration and network economies. On a local scale, APS firms continue their location expansion over time and concentrate in agglomerations where many other APS firms and a greater availability of workforce are present. Simultaneously, they also choose new locations in agglomerations further apart from their present locations. On a supra-local scale, the network grows denser over time. Agglomerations that are attractive for APS firms in 2009 become even more attractive in 2019. Our analysis contributes to an understanding of how interactions amongst cities and firms on a local scale give rise to the empirically observed network patterns on a supra-local scale.

Contemporary West European shantytowns have essentially been studied with qualitative methods. Questions related to their ethnic structure, homophily and interaction with local institutions have not been analysed through large samples and survey data. Based on the example of Romanian and Bulgarian Roma living in shantytowns in the Parisian metropolitan area, we analyse the 'historical' region of origin (autochthony), networks between individuals and households having lived together in a shantytown, as well as some of their attitudes, skills, and behaviour (i.e. expectations as to local welfare, French proficiency, children's schooling). We used a database of slum-dwellers in Paris collected by social workers (N = 12,019). The paper looks at how autochthonies combine with socialisation in shantytowns and with territorial institutional effects of local policies. Evidence shows that while there are limited differences in the socio-professional backgrounds of slum-dwellers, there are several differences in attitudes, behaviour and skills. Moreover, social network analysis shows that these differences are only weakly related to the households' region of origin (autochthony), while they are more correlated to emergent structural clusters of co-habitation connections, where individuals socialise in acting together to build and manage a shantytown. Moreover, local policies at the city level play a role in shaping shantytown dwellers expectations and skills for integration. [ABSTRACT FROM AUTHOR]

Analyzing two-mode networks linking actors to events they attend may help to uncover the structure and evolution of social networks. This classic social network insight is particularly valuable in the analysis of data extracted from contact diaries where contact events produce — and at the same time are the product of relations among participants. Contact events may comprise any number of actors meeting at a specific point in time. In this paper we recall the correspondence between two-mode actor–event networks and hypergraphs, and propose relational hyperevent models (RHEM) as a general modeling framework for networks of time-stamped multi-actor events in which the diarist ("ego") simultaneously meets several of her alters. RHEM can estimate event intensities associated with each possible subset of actors that may jointly participate in events, and test network effects that may be of theoretical or empirical interest. Examples of such effects include preferential attachment, prior shared activity (familiarity), closure, and covariate effects explaining the propensity of actors to co-attend events. Statistical tests of these effects can uncover processes that govern the formation and evolution of informal groups among the diarist's alters. We illustrate the empirical value of RHEM using data comprising almost 2000 meeting events of former British Prime Minister Margaret Thatcher with her cabinet ministers, transcribed from contact diaries covering her first term in office (1979–1983). • Propose relational hyperevent models. • General model framework for time-stamped multi-actor interaction. • Model for actor–event networks with time-stamped events. [ABSTRACT FROM AUTHOR]

Complex networks in real world inevitably suffer from diverse kinds of attacks. Due to the external attacks, some components of a network will be destroyed and therefore will lose their functions. In reality, the components of a network normally interact with one another. As a consequence, the dysfunction of some components is likely to cause the dysfunction of components that rely on the failed components. As the newly failed components may continue to cause the dysfunction of other network components, a system-level cascading dysfunction eventually could happen which can lead to the breakdown of the original network. It is therefore of great significance to assess the robustness of complex networks under attacks. In the literature, many network models and theories have been developed to study the robustness of complex networks. However, the majority of existing studies only investigate multilayer networks, while very little attention is paid to two-mode networks. Two-mode networks are an import ingredient of network sciences. Nevertheless, the structures of two-mode networks are different from that of multilayer networks. As a consequence, theories developed for multilayer networks cannot be applied to two-mode networks. With regard to this, in this paper we put forward a theoretical method to assess the robustness of two-mode networks under node attacks. By taking into account the special structures of two-mode networks as well as making use of probability theory, we therefore put forward the corresponding theory for calculating the robustness of two-mode networks to node failures. In order to verify the correctness of the proposed theory, we carry out simulations on computer-generated two-mode networks with compound Poisson degree distributions. The simulation results are in accordance with what are obtained from our developed theory. The simulation results have validated the correctness of our proposed method for robustness assessment of two-mode networks.

Deterministic blockmodelling is a well‐established clustering method for both exploratory and confirmatory social network analysis seeking partitions of a set of actors so that actors within each cluster are similar with respect to their patterns of ties to other actors (or, in some cases, other objects when considering two‐mode networks). Even though some of the historical foundations for certain types of blockmodelling stem from the psychological literature, applications of deterministic blockmodelling in psychological research are relatively rare. This scarcity is potentially attributable to three factors: a general unfamiliarity with relevant blockmodelling methods and applications; a lack of awareness of the value of partitioning network data for understanding group structures and processes; and the unavailability of such methods on software platforms familiar to most psychological researchers. To tackle the first two items, we provide a tutorial presenting a general framework for blockmodelling and describe two of the most important types of deterministic blockmodelling applications relevant to psychological research: structural balance partitioning and two‐mode partitioning based on structural equivalence. To address the third problem, we developed a suite of software programs that are available as both Fortran executable files and compiled Fortran dynamic‐link libraries that can be implemented in the R software system. We demonstrate these software programs using networks from the literature. [ABSTRACT FROM AUTHOR]

Many real-world large datasets correspond to bipartite graph data settings—think for example of users rating movies or people visiting locations. Although there has been some prior work on data analysis with such bigraphs, no general network-oriented methodology has been proposed yet to perform node classification. In this paper we propose a three-stage classification framework that effectively deals with the typical very large size of such datasets. The stages are: (1) top node weighting, (2) projection to a weighted unigraph, and (3) application of a relational classifier. This paper has two major contributions. Firstly, this general framework allows us to explore the design space, by applying different choices at the three stages, introducing new alternatives and mixing-and-matching to create new techniques. We present an empirical study of the predictive and run-time performances for different combinations of functions in the three stages over a large collection of bipartite datasets with sizes of up to 20 million × 30 million nodes. Secondly, thinking of classification on bigraph data in terms of the three-stage framework opens up the design space of possible solutions, where existing and novel functions can be mixed and matched, and tailored to the problem at hand. Indeed, in this work a novel, fast, accurate and comprehensible method emerges, called the SW-transformation, as one of the best-performing combinations in the empirical study. [ABSTRACT FROM AUTHOR]

During the past 5 to 10 years, an estimation method known as eLasso has been used extensively to produce symptom networks (or, more precisely, symptom dependence graphs) from binary data in psychopathological research. The eLasso method is based on a particular type of Ising model that corresponds to binary pairwise Markov random fields, and its popularity is due, in part, to an efficient estimation process that is based on a series of l1-regularized logistic regressions. In this article, we offer an unprecedented critique of the Ising model and eLasso. We provide a careful assessment of the conditions that underlie the Ising model as well as specific limitations associated with the eLasso estimation algorithm. This assessment leads to serious concerns regarding the implementation of eLasso in psychopathological research. Some potential strategies for eliminating or, at least, mitigating these concerns include (a) the use of partitioning or mixture modeling to account for unobserved heterogeneity in the sample of respondents, and (b) the use of co-occurrence measures for symptom similarity to either replace or supplement the covariance/correlation measure associated with eLasso. Two psychopathological data sets are used to highlight the concerns that are raised in the critique. We present the first principled critique of the Ising model and the associated eLasso method. The Ising model is a form of a pairwise Markov random field that is used to model binary data. The current approach utilizes a set of logistic regressions to obtain parameter estimates, with the final model being chosen with the so-called eLasso method to mitigate against overfitting. Throughout, we highlight why application of this model to data with traits that are commonly found in psychopathological data may be problematic due to issues such as sample size, density, asymmetric parameter weights, and so on. Specifically, the necessary sample size for fitting these models is dependent on the density (e.g., the number of connections) of the network, with a strong preference being given to networks that are not dense. Unfortunately, several (if not the vast majority of) psychopathology disorders have been conceptualized as cohesive traits, and as such, methods used to measure them assume that all of the items arise from a common factor. This standard assumption leads to items that are highly intercorrelated, resulting in networks that are dense—exactly the situation that is not desired for the predominant estimation techniques of the Ising model. In turn, we recommend a partitioning approach that may help address some of these issues. Beyond this issue, we assess the appropriateness of averaging parameter asymmetric parameter estimates to achieve symmetric parameter estimates—a practice that could result in the loss of information. Finally, we show that it is likely that much of the data analyzed with these methods do not arise from the same homogeneous population; as such, we introduce a partitioning method to aid in determining if several "subnetworks" are being averaged together when they are fit together as one big network, resulting in global findings that are not consistent with any local structures. [ABSTRACT FROM AUTHOR]

In policymaking, actors are likely to take the preferences of others into account when strategically positioning themselves. However, there is a lack of research that conceives of policy preferences as an interdependent system. In order to analyse interdependencies, we link actors to their policy preferences in water protection, which results in an actor-instrument network. As actors exhibit multiple preferences, a complex two-mode network between actors and policies emerges. We analyse whether actors exhibit interdependent preference profiles given shared policy objectives or social interactions among them. By fitting an exponential random graph model to the actor-instrument network, we find considerable clustering, meaning that actors tend to exhibit preferences for multiple policy instruments in common. Actors tend to exhibit interdependent policy preferences when they are interconnected, that is, they collaborate with each other. By contrast, actors are less likely to share policy preferences when a conflict line divides them. [ABSTRACT FROM AUTHOR]

• Recent work has begun to use relational approaches to study taste. • However, this work relies on vague genre labels. • These labels hide macrogenres, overstating boundaries. • I propose a link-clustering approach. • The proposed approach uncovers valid microgenres. Recent work in the sociology of taste has begun to grapple with the relational properties of traditional survey-based data using techniques inspired by network analysis. Despite productive results from this endeavor, critics rightly question the face and ecological validity of the vague macrogenre labels included in standard arts participation surveys (e.g., Classical, Rock, Rap) which feed into these novel methods. In this paper, I propose a link-clustering approach for discovering focused microgenres from standard survey-based information on cultural tastes, exploiting the underlying relational patterns realized by the indirect connectivity structure of genres (via people) in a two-mode network. The link-clustering approach partially answers two of the challenges of macrogenre critics: The fact that actual genres are overlapping and not crisply bounded and that there is hidden heterogeneity within the broad labels we usually focus on. To showcase the fruitfulness of the proposed approach, I engage in two "case studies" featuring the vague macro genres of "Heavy Metal" and "Latin/Salsa" music and show the focused microgenres produced by the link clustering procedure are segmented in ways that help resolve puzzles that have emerged in previous work. [ABSTRACT FROM AUTHOR]

This study aims to answer the question to what extent different types of networks can be used to predict future co-authorship among authors.

Abstract This paper applies a two-mode social network analysis approach to identify the brokers in knowledge networks resulting from interactions taking place at specialized seminars and courses organized in a tourism destination. Empirical findings show that technology and innovation centers can be the leading hub of 'administered knowledge networks' – understood as efficient knowledge governance arrangements – in which a wide variety of actors, including universities, private-sector associations, public organizations, and firms play complementary roles depending on the nature of the interactions (formal transfer versus informal exchange flows). These structures are found to be fundamental for the functioning of localized systems of learning. Highlights • Administered knowledge networks' promote innovation in tourism destinations. • Technology and innovation centers can lead destination knowledge networks. • Formal and informal interactions create knowledge networks with distinct structures. • Networking and knowledge dissemination shape paths of tourism destinations. • Social network analysis techniques serve to identify the brokers in knowledge networks. [ABSTRACT FROM AUTHOR]

Highlights • Application of a novel method for computing centrality in two-mode networks. • Testing seven different betweenness measures to identify criminal leaders • Dual projection approaches perform better in identifying leaders. • Confirmation of the importance of brokerage for criminal networks. Abstract Brokerage is crucial for dark networks. In analyzing communications among criminals, which naturally induce bipartite networks, previous studies have focused on the classic Freeman's betweenness, conceived for one-mode matrices and possibly biasing the results. We explore different betweenness centrality including three inspired by the dual projection approach recently suggested by Everett and Borgatti 2013. We test these measures in identifying criminal leaders in a meeting participation network. Despite the expected high correlations among them, the measures yield different node rankings, capturing different characteristics of brokerage. Overall, the dual projection approaches show higher success than classic approaches in identifying the criminal leaders. [ABSTRACT FROM AUTHOR]

Two mode social network data consisting of actors attending events is a common type of social network data. For these kinds of data it is also common to have additional information about the timing or sequence of the events. We call data of this type two-mode temporal data. We explore the idea that actors attending events gain information from the event in two ways. Firstly the event itself may provide information or training; secondly, as co-attendees interact, they may pass on skills or information they have gleaned from other events. We propose a method of measuring these gains and demonstrate its usefulness using the classic Southern Women Data and a covert network dataset. [ABSTRACT FROM AUTHOR]

Young adults with autism spectrum disorder (ASD) face poor employment outcomes following transition from school to adult life. Social network analysis is a useful approach for examining service patterns associated with employment success for this population. An advantage of this approach is its focus on the interdependence of variables rather than individual predictors. This study applies network methodology to examine the relations between vocational rehabilitation services and young adults with ASD to predict employment status. Using the Rehabilitation Services Administration (RSA-911) data set, participants included 2,219 individuals with ASD between the ages of 16 and 24 served by the public vocational rehabilitation system and closed as either competitively employed or not employed. A two-mode network was constructed such that a relation was defined for each service an individual received. Results from a core-periphery analysis indicated that of the 22 services available, core services included assessment, counseling/guidance, job placement, on-the-job support, job search support, and transportation services. Follow-up analyses suggested that the greater number of these six core services an individual received, the better the employment outcome. Findings highlight that these services should be viewed as interconnected and suggest a set of six core services that may be particularly beneficial for this population. [ABSTRACT FROM AUTHOR]

In this paper we propose a new method for studying local and global clustering in networks employing random walk pairs. The method is intuitive and directly generalizes standard local and global clustering coefficients to weighted networks and networks containing nodes of multiple types. In the case of two-mode networks the values obtained for commonly considered social networks are in sharp contrast to those obtained, for instance, by the method of Opsahl (2013) , and provide a different viewpoint for clustering. The approach is also applicable in questions related to the general study of segregation and homophily. Applications to existent data sets are considered. [ABSTRACT FROM AUTHOR]

Deterministic blockmodeling of a two-mode binary network matrix based on structural equivalence is a well-known problem in the social network literature. Whether implemented in a standalone fashion, or embedded within a metaheuristic framework, a popular relocation heuristic (RH) has served as the principal solution tool for this problem. In this paper, we establish that a two-mode KL-median heuristic (TMKLMedH) seeks to optimize the same criterion as the RH for deterministic blockmodeling. The TMKLMedH runs much faster than the RH, so many more restarts of the TMKLMedH can be accomplished when the two methods are constrained to the same time limit. Three computational comparisons of RH and TMKLMedH were conducted using both synthetic and real-world networks. In all three comparisons, the superiority of TMKLMedH was unequivocal. [ABSTRACT FROM AUTHOR]

In the context of research collaboration and co-authorship, we studied scholars’ scientific achievements and success, based on their collection of shared publications. By means of a novel regression model, which exploits the two-mode structure of co-authorship, we translated paper scientific impact into author professional achievement , to simultaneously account for the effect of paper properties (access status, funding bodies, etc.) as well as author demographic and behavioral characteristics (gender, nationality) on academic success and impact. After a detailed analysis of the proposed statistical procedure, we illustrated our approach with an empirical analysis of a co-authorship network based on 1007 scientific articles. [ABSTRACT FROM AUTHOR]