Link prediction in growing networks with aging

The link prediction problem aims to predict new links for future, or missing links or unobserved links in complex networks. Traditional link prediction methods are mostly concentrated on static networks. In this paper, we mainly explore link prediction problems in growing networks. We propose a series of time-sliced metrics to estimate the likelihood of the existence of missing links between two nodes for evolving networks based on traditional link prediction indices. We found that these proposed metrics outperform existing metrics for growing networks with time decay factor, especially when the decay factors are small. Besides, to improve prediction efficiency and practicability, we propose the function expressions for optimal slice number and decay factor for real-world networks. The formula enables us to estimate the aging speed of real growing networks, resulting in accurate and fast prediction of missing links in growing networks.     

FIRM HETEROGENEITY AND THE PATTERN OF R&D COLLABORATIONS

We consider an oligopoly setting in which firms form pairwise collaborative links in research and development with other firms. Each collaboration generates a value that depends on the identity of the firms that collaborate. First, we provide properties satisfied by pairwise equilibrium networks and efficient networks. Second, we use these properties in two types of situation: (1) there are two groups of firms, and the value of a collaboration is higher when firms belong to the same group; (2) some firms have more innovative capabilities than others. These two situations provide clear insights about how firms' heterogeneity affects both equilibrium and efficient networks. We also show that the most valuable collaborative links do not always appear in equilibrium, and a public policy that increases the value of the most valuable links may lead to a loss of social welfare. (JEL C70, L13, L20)     

Trust and partner selection in social networks: An experimentally grounded model

This article investigates the importance of the endogenous selection of partners for trust and cooperation in market exchange situations, where there is information asymmetry between investors and trustees. We created an experimental-data driven agent-based model where the endogenous link between interaction outcome and social structure formation was examined starting from heterogeneous agent behaviour. By testing various social structure configurations, we showed that dynamic networks lead to more cooperation when agents can create more links and reduce exploitation opportunities by free riders. Furthermore, we found that the endogenous network formation was more important for cooperation than the type of network. Our results cast serious doubt about the static view of network structures on cooperation and can provide new insights into market efficiency.     

Structure and bias in the network autocorrelation model

In a recent paper (Mizruchi and Neuman, 2008), we showed that estimates of ρ in the network autocorrelation model exhibited a systematic negative bias and that the magnitude of this bias increased monotonically with increases in network density. We showed that this bias held regardless of the size of the network, the number of exogenous variables in the model, and whether the matrix W was normalized or in raw form. The networks in our simulations were random, however, which raises the question of the extent to which the negative bias holds in various structured networks. In this paper, we reproduce the simulations from our earlier paper on a series of networks drawn to represent well-known structures, including star, caveman, and small-world structures. Results from these simulations indicate that the pattern of negative bias in ρ continues to hold in all of these structures and that the negative bias continues to increase at increasing levels of density. Interestingly, the negative bias in ρ is especially pronounced at extremely low-density levels in the star network. We conclude by discussing the implications of these findings.     

Clearing the FOG: Fuzzy,overlapping groups for social networks

Humans are well known to belong to many associative groups simultaneously, with various levels of affiliation. However, most group detection algorithms for social networks impose a strict partitioning on nodes, forcing entities to belong to a single group. Link analysis research has produced several methods which detect multiple memberships but force equal membership. This paper extends these approaches by introducing the FOG framework, a stochastic model and group detection algorithm for fuzzy, overlapping groups. We apply our algorithm to both link data and network data, where we use a random walk approach to generate rich links from networks. The results demonstrate that not only can fuzzy groups be located, but also that the strength of membership in a group and the fraction of individuals with exclusive membership are highly informative of emerging group dynamics.     

Social network capital, economic mobility and poverty traps

This paper explores the role social network capital might play in facilitating poor agents?? escape from poverty traps. We model and simulate endogenous link formation among households heterogeneously endowed with both traditional and social network capital who make investment and technology choices over time in the absence of financial markets and faced with multiple production technologies featuring different fixed costs and returns. We show that social network capital can either complement or substitute for productive assets in facilitating some poor households?? escape from poverty. However, the voluntary nature of costly link formation also creates exclusionary mechanisms that impede some poor households?? use of social network capital. Through numerical simulation, we show that the ameliorative potential of social networks therefore depends fundamentally on the broader socio-economic wealth distribution in the economy, which determines the feasibility of social interactions and the net intertemporal benefits resulting from endogenous network formation. In some settings, targeted public transfers to the poor can crowd-in private resources by inducing new social links that the poor can exploit to escape from poverty.     

BEHAVIORAL PATTERNS IN SOCIAL NETWORKS

In this article, we focus on the analysis of individual decision‐making for the formation of social networks, using experimentally generated data. We analyze the determinants of the individual demand for links under the assumption of agents' static expectations and identify patterns of behavior that correspond to three specific objectives: players propose links so as to maximize expected profits (myopic best response strategy); players attempt to establish the largest number of direct links (reciprocator strategy); and players maximize expected profits per direct link (opportunistic strategy). These strategies explain approximately 74% of the observed choices. We demonstrate that they are deliberately adopted and, by means of a finite mixture model, well identified and separated in our sample. (JEL C33, C35, C90, D85)     

Dynamic exchange networks

Considering the theoretical and empirical untenability of static exchange networks, researchers have asked how exchange outcomes change when links are added or deleted. The present paper assesses the validity of seemingly sensible propositions concerning the effects of adding and deleting a link on (i) the payoffs of the actors in the link, (ii) the payoffs of actors in neighboring links and (iii) the variance of payoffs in the exchange network. The propositions were examined by applying expected value theory (EVT) to all 13,597 networks up to size 8. All propositions were falsified. Some falsifications of propositions could be attributed to EVTs prediction that actors use sub-optimal exchange relations. Since other well-known theories of exchange, like power-dependence theory and network exchange theory, also predict that actors use sub-optimal relations, these results are robust to selection of the theory of exchange.     

Bridging: Locating critical connectors in a network

This paper proposes several measures for bridging in networks derived from Granovetter's (1973) insight that links which reduce distances in a network are important structural bridges. Bridging is calculated by systematically deleting links and calculating the resultant changes in network cohesion (measured as the inverse average path length). The average change for each node's links provides an individual level measure of bridging. We also present a normalized version which controls for network size and a network-level bridging index. Bridging properties are demonstrated on hypothetical networks, empirical networks, and a set of 100 randomly generated networks to show how the bridging measure correlates with existing network measures such as degree, personal network density, constraint, closeness centrality, betweenness centrality, and vitality. Bridging and the accompanying methodology provide a family of new network measures useful for studying network structure, network dynamics, and network effects on substantive behavioral phenomenon.     

A comparative study of social network models: Network evolution models and nodal attribute models

This paper reviews, classifies and compares recent models for social networks that have mainly been published within the physics-oriented complex networks literature. The models fall into two categories: those in which the addition of new links is dependent on the (typically local) network structure (network evolution models, NEMs), and those in which links are generated based only on nodal attributes (nodal attribute models, NAMs). An exponential random graph model (ERGM) with structural dependencies is included for comparison. We fit models from each of these categories to two empirical acquaintance networks with respect to basic network properties. We compare higher order structures in the resulting networks with those in the data, with the aim of determining which models produce the most realistic network structure with respect to degree distributions, assortativity, clustering spectra, geodesic path distributions, and community structure (subgroups with dense internal connections). We find that the nodal attribute models successfully produce assortative networks and very clear community structure. However, they generate unrealistic clustering spectra and peaked degree distributions that do not match empirical data on large social networks. On the other hand, many of the network evolution models produce degree distributions and clustering spectra that agree more closely with data. They also generate assortative networks and community structure, although often not to the same extent as in the data. The ERGM model, which turned out to be near-degenerate in the parameter region best fitting our data, produces the weakest community structure.     

Health and the structure of adolescent social networks

Much research has explored the role of social networks in promoting health through the provision of social support. However, little work has examined how social networks themselves may be structured by health. This article investigates the link between individuals' health and the characteristics of their social network positions. We first develop theoretical predictions for how health may influence the structure of adolescent networks. We then test these predictions using longitudinal analysis of the National Longitudinal Study of Adolescent Health (Add Health). We find important relationships between the health status of adolescents and the characteristics of the social network positions within which they are embedded. Overall we find that adolescents in poor health form smaller local networks and occupy less central global positions than their healthy peers. These results also have implications for social network research, expanding the scope of factors responsible for the network positions individuals occupy.     

The coevolution of trade agreements and investment treaties: Some evidence from network analysis

Regional trade agreements (RTAs) and bilateral investment treaties (BITs) are expected to promote trade and investment relationships. One critical feature of such agreements is the network, so the multiplex coevolution of RTAs and BITs should be captured by the dynamics of their two networks. Although many studies have examined the roles of RTAs and BITs, most studies do not account for crucial network properties. This study explores how RTAs and BITs coevolve by applying a stochastic actor-oriented model of multiplex network evolution. In particular, we examine the roles of (i) cross-network dyadic interinfluences and (ii) within- and cross-network preferential attachments to discuss the dynamic relationships between RTAs and BITs. The results are as follows. First, our estimation supports cross-network dyadic interinfluences. Countries that sign a BIT are willing to establish an RTA, while those that sign an RTA are reluctant to establish a BIT. Second, concerning preferential attachments, countries prefer to sign BITs with partners that have more RTA and BIT links. However, countries tend to form RTAs with partners that have more BIT links but are reluctant to form RTAs with those that have more RTA links. We discuss possible justifications for these results, including arguments regarding the benefits and costs associated with the formation of RTAs and BITs.     

Evolutions of personal networks and life events

Networks of personal relations evolve over time. They reflect and go with processes of socialization. Their history and dynamics contribute to their present structure. The number of people involved in them and their composition change, as does the quality of the links that constitute them. What life events might influence these changes, or possibly even explain them?Drawing on a qualitative survey of a panel of 66 young people living originally in Normandy (France), who were questioned every three years, we attempt here to find a relation between the evolution of their personal networks and the events marking their entry into adult life.Do their networks expand or contract, do they move regularly or in stages? What are the links that appear, disappear or change? What events are likely to influence changes in these links and in the networks as a whole?We begin by examining the changes in the young people's networks during the survey's three waves. We then identify the life events that took place in the intervals, focusing in particular on entry into the labour market, geographical mobility, setting up house with a partner and the birth of children in the household. This enables us to advance some hypotheses about the impact of these events on the evolution of networks and to illustrate our argument with a few significant examples.     

Explaining the power-law degree distribution in a social commerce network

Social commerce is an emerging trend in which online shops create referral hyperlinks to other shops in the same online marketplace. We study the evolution of a social commerce network in a large online marketplace. Our dataset starts before the birth of the network (at which points shops were not linked to each other) and includes the birth of the network. The network under study exhibits a typical power-law degree distribution. We empirically compare a set of edge formation mechanisms (including preferential attachment and triadic closure) that may explain the emergence of this property. Our results suggest that the evolution of the network and the emergence of its power-law degree distribution are better explained by a network evolution mechanism that relies on vertex attributes that are not based on the structure of the network. Specifically, our analysis suggests that the power-law degree distribution emerges because shops prefer to connect to shops with more diverse assortments, and assortment diversity follows a power-law distribution. Shops with more diverse assortments are more attractive to link to because they are more likely to bring traffic from consumers browsing the WWW. Therefore, our results also imply that social commerce networks should not be studied in isolation, but rather in the context of the broader network in which they are embedded (the WWW).     

Ranking terrorists in networks: A sensitivity analysis of Al Qaeda's 9/11 attack

All over the world, intelligence services are collecting data concerning possible terrorist threats. This information is usually transformed into network structures in which the nodes represent the individuals in the data set and the links possible connections between these individuals. Unfortunately, it is nearly impossible to keep track of all individuals in the resulting complex network. Therefore, Lindelauf et al. (2013) introduced a methodology that ranks terrorists in a network. The rankings that result from this methodology can be used as a decision support system to efficiently allocate the scarce surveillance means of intelligence agencies. Moreover, usage of these rankings can improve the quality of surveillance which can in turn lead to prevention of attacks or destabilization of the networks under surveillance.The methodology introduced by Lindelauf et al. (2013) is based on a game theoretic centrality measure, which is innovative in the sense that it takes into account not only the structure of the network but also individual and coalitional characteristics of the members of the network. In this paper we elaborate on this methodology by introducing a new game theoretic centrality measure that better takes into account the operational strength of connected subnetworks.Moreover, we perform a sensitivity analysis on the rankings derived from this new centrality measure for the case of Al Qaeda's 9/11 attack. In this sensitivity analysis we consider firstly the possible additional information available about members of the network, secondly, variations in relational strength and, finally, the absence or presence of a small percentage of links in the network. We also introduce a case specific method to compare the different rankings that result from the sensitivity analysis and show that the new centrality measure is robust to small changes in the data.     

Basic notions for the analysis of large two-mode networks

Many large real-world networks actually have a two-mode nature: their nodes may be separated into two classes, the links being between nodes of different classes only. Despite this, and despite the fact that many ad hoc tools have been designed for the study of special cases, very few exist to analyse (describe, extract relevant information) such networks in a systematic way. We propose here an extension of the most basic notions used nowadays to analyse large one-mode networks (the classical case) to the two-mode case. To achieve this, we introduce a set of simple statistics, which we discuss by comparing their values on a representative set of real-world networks and on their random versions. This makes it possible to evaluate their relevance in capturing properties of interest in two-mode networks.     

Using Social Network Analysis to Explore Social Movements: A Relational Approach

This paper uses a ‘relational’ approach to network analysis to demonstrate the linkages between different types of environmental organizations in London. A ‘relational’ approach was used to avoid problems associated with ‘positional’ approaches such as structural determinism, subjectively defined and misleadingly labelled blocks of ‘approximately’ equivalent actors, and reification of the action/issue basis of networks. The paper also explores definitions of social/environmental movements. Whilst broadly agreeing with Diani's consensual definition of a social movement, it argues that we need to be much more precise about the type and intensity of networking required; it must be more than informal or cursory, and should bind individuals and organizations into collaborative networks. Evidence from a survey of 149 environmental organizations and qualitative interviews with key campaigners suggests that whilst many organizations might share information, it is often stockpiled or ignored, hardly creating the kinds of network links that might lead to shared movement identity. The kinds of links that do bind movements are collaborative. In practice, in the environmental movement in London, conservationists tend neither to share information nor to engage in the collective action events of reformist or radical organizations, suggesting that conservationists should perhaps not be considered part of the movement.     

Peer influence groups: identifying dense clusters in large networks

Sociologists have seen a dramatic increase in the size and availability of social network data. This represents a poverty of riches, however, since many of our analysis techniques cannot handle the resulting large (tens to hundreds of thousands of nodes) networks. In this paper, I provide a method for identifying dense regions within large networks based on a peer influence model. Using software familiar to most sociologists, the method reduces the network to a set of m position variables that can then be used in fast cluster analysis programs. The method is tested against simulated networks with a known small-world structure showing that the underlying clusters can be accurately recovered. I then compare the performance of the procedure with other subgroup detection algorithms on the MacRea and Gagnon prison friendship data and a larger adolescent friendship network, showing that the algorithm replicates other procedures for small networks and outperforms them on the larger friendship network.