Let’s Talk About Refugees: Network Effects Drive Contributor Attention to Wikipedia Articles About Migration-Related Topics

Lerner, Jürgen; Lomi, Alessandro

doi:10.1007/978-3-030-05414-4_17

Cited by 2 publications

(10 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their model does not explain user activity rates but rather specifies dyadic probabilities to undo or redo contributions of other target users, given that a source user becomes active on the focal article. Previous work that seems to be the closest to this paper is a recent article of Lerner & Lomi (2019a) which analyzes an REM for edit and talk events on Wikipedia articles about migration-related topics (also discussed in the introduction). Thus, Lerner & Lomi (2019a) analyze a thematically delineated subnetwork.…”

Section: Empirical Setting: Network Analysis Of Collaboration In Wikimentioning

confidence: 99%

“…Previous work that seems to be the closest to this paper is a recent article of Lerner & Lomi (2019a) which analyzes an REM for edit and talk events on Wikipedia articles about migration-related topics (also discussed in the introduction). Thus, Lerner & Lomi (2019a) analyze a thematically delineated subnetwork. They apply case-control sampling but do not sample from the observed events and do not experimentally vary sample sizes.…”

Section: Empirical Setting: Network Analysis Of Collaboration In Wikimentioning

confidence: 99%

“…An alternative to these two sampling schemes would be to restrict the analysis to subnetworks that are sufficiently small, for instance, by considering only events among a specific subset of nodes. An example of this strategy is given by Lerner & Lomi (2019a) who analyze edit and discussion events in Wikipedia restricted to articles about "migration-related topics, " which results in some 4,000 articles and 87,000 users connected by 950,000 events. Lerner & Lomi (2019a) applied case-control sampling from the risk set but did not sample from the observed events among this restricted set of nodes.…”

Section: Introductionmentioning

confidence: 99%

“…An example of this strategy is given by Lerner & Lomi (2019a) who analyze edit and discussion events in Wikipedia restricted to articles about "migration-related topics, " which results in some 4,000 articles and 87,000 users connected by 950,000 events. Lerner & Lomi (2019a) applied case-control sampling from the risk set but did not sample from the observed events among this restricted set of nodes. We claim that the sampling strategy proposed and analyzed in this paper, which samples uniformly from all events, is preferable to the analysis of a subnetwork for at least two reasons.…”

Section: Introductionmentioning

confidence: 99%

“…Second, if we restrict the analysis to subnetworks, the computation of explanatory variables is potentially incorrect. In the example from Lerner & Lomi (2019a), Wikipedia users might contribute to articles that are not in the chosen subset so that, for instance, the out-degree, in-degree, or four-cycle statistics, see Equations (8)-(10), might be computed incorrectly. In brief, restricting the analysis to subnetworks needs a strong assumption about the modularity or quasi-decomposability of the relational system of interest (Newman, 2006;Simon, 1996Simon, , 1977.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Reliability of relational event model estimates under sampling: How to fit a relational event model to 360 million dyadic events

Lerner

Lomi

2019

Net Sci

Self Cite

View full text Add to dashboard Cite

We assess the reliability of relational event model parameters estimated under two sampling schemes:(1) uniform sampling from the observed events and (2) case-control sampling which samples non-events, or null dyads ("controls"), from a suitably defined risk set. We experimentally determine the variability of estimated parameters as a function of the number of sampled events and controls per event, respectively. Results suggest that relational event models can be reliably fitted to networks with more than 12 million nodes connected by more than 360 million dyadic events by analyzing a sample of some tens of thousands of events and a small number of controls per event. Using data that we collected on the Wikipedia editing network, we illustrate how network effects commonly included in empirical studies based on relational event models need widely different sample sizes to be estimated reliably. For our analysis we use an open-source software which implements the two sampling schemes, allowing analysts to fit and analyze relational event models to the same or other data that may be collected in different empirical settings, varying sample parameters or model specification.hampered by runtime complexity (Foucault Welles et al. 2014) -a problem that is rooted in the likelihood function which normalizes event rates on dyads that experience events by the rates on all dyads that could have possibly experienced an event at the given point in time. The corresponding risk set can be huge, since its size is often quadratic in the number of nodes. For example, in Wikipedia -the setting for the data that we examine in the empirical part of this paper -more than 6 million users contribute to one or several of more than 5 million encyclopedic articles, giving rise to more than 360 million dyadic events. Thus, at given points in time a dyadic event could occur on more than 30 trillion (3 × 10 13 ) dyads. Computing explanatory variables (statistics) for each of these dyads is unfeasible even for a single observed event -much less so for all 360 million events. Such problems are rather typical since -as mentioned above -large quantities of information on relational events are often collected with automatic data-collection technologies which in turn can easily yield large, or very large networks.Empirical studies applying REM, therefore, have often been limited to networks with a rather small number of nodes (Foucault Welles et al. 2014;Lerner et al. 2013;Vu et al. 2017). Exceptions include studies exploiting a "sparsity condition," namely that a single observed event changes the values of some statistics not for all dyads in the risk set but only for a limited subset (Perry and Wolfe 2013;Hunter et al. 2011). For instance, an observed event on a dyad (a, b) changes the out-degree statistic only for all dyads with source aimplying update costs that are linear, rather than quadratic in the number of nodes. This approach, however, requires to develop specific estimation algorithms for different model statistics. Moreover, it does not...

show abstract

Section: Empirical Setting: Network Analysis Of Collaboration In Wikimentioning

confidence: 99%

Section: Empirical Setting: Network Analysis Of Collaboration In Wikimentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Reliability of relational event model estimates under sampling: How to fit a relational event model to 360 million dyadic events

Lerner

Lomi

2019

Net Sci

Self Cite

View full text Add to dashboard Cite

show abstract

Separating the Wheat from the Chaff: Bayesian Regularization in Dynamic Social Networks

Karimova¹,

Mulder²,

Leenders³

2022

Preprint

View full text Add to dashboard Cite

In recent years there has been an increasing interest in the use of relational event models for dynamic social network analysis. The basis of these models is the concept of an "event", defined as a triplet of time, sender, and receiver of some social interaction. The key question that relational event models aim to answer is what drives social interactions among actors.Researchers often consider a very large number of predictors in their studies (including exogenous variables, endogenous network effects, and various interaction effects). The problem is however that employing an excessive number of effects may lead to model overfitting and inflated Type-I error rates. Consequently, the fitted model can easily become overly complex and the implied social interaction behavior becomes difficult to interpret.A potential solution to this problem is to apply Bayesian regularization using shrinkage priors. In this paper, we propose Bayesian regularization methods for relational event models using four different priors: a flat prior model with no shrinkage effect, a ridge estimator with a normal prior, a Bayesian lasso with a Laplace prior, and a horseshoe estimator with a numerically constructed prior that has an asymptote at zero. We develop and use these models for both an actor-oriented relational event model and a dyad-oriented relational event model. We show how to apply Bayesian regularization methods for these models and provide insights about which method works best and guidelines how to apply them in practice. Our results show that shrinkage priors can reduce Type-I errors while keeping reasonably high predictive performance and yielding parsimonious models to explain social network behavior.

show abstract

Let’s Talk About Refugees: Network Effects Drive Contributor Attention to Wikipedia Articles About Migration-Related Topics

Cited by 2 publications

References 32 publications

Reliability of relational event model estimates under sampling: How to fit a relational event model to 360 million dyadic events

Reliability of relational event model estimates under sampling: How to fit a relational event model to 360 million dyadic events

Separating the Wheat from the Chaff: Bayesian Regularization in Dynamic Social Networks

Contact Info

Product

Resources

About