Sunbelt 2026 - Daytona Beach

Many sociological processes unfold as sequences of temporally ordered interaction events between entities. Leveraging the availability of time-stamped data, the Relational Event Model (REM) provides a powerful framework for generative modeling of such dynamic networks. REMs capture how node and edge characteristics, together with past interactions, shape the evolution of these processes. The essential temporal information embedded in relational event sequences has motivated advances in the specification of covariates and development of inference techniques.

In this workshop, we will introduce the foundations of REMs and show how to construct covariates that represent exogenous drivers, endogenous mechanisms, and temporal features of these processes. We will then examine likelihood-based inference methods for estimating covariate effects and discuss extensions that enhance the flexibility of REMs, including non-linear and time-varying influences as well as random effects to account for network and actor heterogeneity.

Workshop Agenda:

1. Core REMs: introduction to REM formulation and the inclusion of time-aware exogenous and endogenous variables.

2. REM inference: overview of likelihood-based estimation methods.

3. Non-Linear REMs: modeling non-linear and time-varying covariate effects while accounting for network and actor heterogeneity.

4. Practical Tutorial with R Studio: applying REMs to empirical datasets.

Prerequisites: Familiarity with R. Previous experience with the statnet packages network and sna is helpful but not required.

Synopsis:

This workshop will provide an introductory tutorial on using exponential-family random graph models (ERGMs) for statistical modeling of social networks, using a hands-on approach to fitting these models to data. The ERGM framework allows for the specification, estimation, and simulation of models that incorporate the complex dependencies within networks, and provides a general and flexible means of representing them. The session will demonstrate ERG modeling using the statnet software in R.

Topics covered within this session include: an overview of the ERGM framework; defining and fitting models to empirical data; interpretation of model coefficients; goodness-of-fit and model adequacy checking; simulation of networks using ERG models; degeneracy assessment and avoidance; and modeling and simulation of complete networks from egocentrically sampled data.  Familiarity with basic descriptive network concepts and statistical methods for network analysis within the R/statnet platform is recommended.  Attendees are expected to have had some prior exposure to R, but extensive experience is not assumed.

statnet is a collection of integrated packages for the R statistical computing environment that support the representation, manipulation, visualization, modeling, simulation, and analysis of network data. statnet is developed and maintained by a team of volunteer developers, and is released under the GNU Public License. statnet packages can be used with any computing platform that supports R (including Windows, Linux, and Mac).  The software supports statistical analysis of large networks, temporal network analysis and valued ties, with utilities for missing and sampled data.

The goal of this workshop is to provide participants an orientation to conducting personal networks research within Network Canvas and the opportunity to master the skills necessary to apply these tools within their specific domain of interest. Network Canvas (http://www.networkcanvas.com), is a free and open-source software suite that facilitates the collection of self-reported social network data, comprised of applications to support both in-person interviewer-assisted environments as well as remote self-administered studies.

In this workshop, we will provide an overview of Architect, the Network Canvas visual survey builder, as well as Interviewer, the Network Canvas app used to collect data directly from participants within an in-person research design. We will also provide an overview of Fresco, the newest Network Canvas tool designed for remote network surveying. Finally, we will explore data export in Interviewer and Fresco, and a brief orientation to analysis. Expect the opportunity to engage in hands-on exercises during the session with assistance from our team.

When completed, you will acquire the skills to:

• Design an egocentric or whole network survey
• Deploy and manage a study, whether in-person or remote
• Obtain study data in Interviewer and Fresco, and export it for analysis

This three-hour, hands-on workshop introduces participants to a suite of user-friendly tools, featuring the PLACE Plot platform and several open-source software tools, for developing and analyzing social network analysis (SNA) surveys for inter-organizational policy networks. Designed for researchers, evaluators, and policy practitioners, PLACEPlot streamlines the process of collecting high-quality relational data to map collaboration across agencies, organizations, and sectors.

The workshop begins with an overview of policy network analysis frameworks—emphasizing how SNA can illuminate patterns of collaboration, boundary spanning, and resource flow within complex policy systems. Participants will then explore PLACEPlot’s intuitive interface to design and deploy customized network surveys, manage respondent data, and generate real-time network visualizations without requiring advanced coding skills.

In the second segment, participants will learn how to connect survey outputs with RShiny applications for interactive reporting and stakeholder engagement. This portion highlights how to translate network data into meaningful visual narratives and dashboards that inform decision-making and drive collaboration.

By the end of the session, attendees will be able to (1) design and distribute SNA surveys using PLACEPlot, (2) interpret and visualize network data for policy insights, and (3) build interactive RShiny tools that make network findings accessible and actionable for diverse stakeholders.

Social network analysis has relied mainly on time-aggregated data and individual node connections. However, advances in data collection technologies now provide large amounts of time-stamped and hypernetwork information. Examples of such datasets include email multicast communication data and citation networks. Whereas methodological developments in temporal network science have expanded the toolkit for describing time-stamped and hypergraph data, relational hyper-event modeling has emerged as a central approach for the statistical modeling of the dynamic structures these data reveal. Recent contributions have made the Relational Hyper Event Model (RHEM) even more flexible, allowing it to address a range of applied demands.

In this workshop, we aim to present RHEMs, beginning with their core properties and progressing to their more novel modeling capacities, highlighting how they can be employed to address empirical questions.

Workshop Agenda:

• Core RHEMs: computing hyperevent covariates; formulating, estimating, and interpreting linear RHEMs.
• Non-Linear RHEMs: modeling non-linear, time-varying covariate effects while accounting for network and actor heterogeneity.
• Practical Tutorial with eventnet and R Studio: applying RHEMs to empirical datasets.
• Emerging Research Directions: exploring new questions and potential extensions for RHEMs.

The workshop focuses on the use of mixed methods research designs when studying whole and ego-centered social networks. The workshop will be conducted in two parts. The first part introduces social network qualitative research and the principles of mixed methods research designs and its contributions to the study of social networks, pointing out advantages and challenges of this approach. Illustrations of the theoretical and methodological aspects are given by bringing examples from a variety of fields of research. The second part is devoted to the presentation of concrete procedures to apply mixed methods in network research both at the level of data collection and analysis. This part includes an introduction of different approaches to the collection of whole and ego-centered network data, i.e. interviews, ethnographic methods, archival data, together with visual instruments. It then moves to the analysis of the quantitative and qualitative dimensions of network relationships and structures in a mixed method perspective.

Socio-semantic network analysis (Basov and Roth, 2025; Basov et al., 2020; Roth and Cointet, 2010) explicitly links social structures (e.g., collaboration, advice, or friendship) and semantic structures (e.g., co-definitions or similarities between words, notions, or concepts). Such as an association between the terms ‘networks’ and ‘culture’ used by a pair of academics who are connected by a collaborative tie of co-editing. Ensembles of socio-semantic patterns are analysed to explain the – traditionally implicit and interpretively addressed – relation between social and cultural structures to formally grasp and model contextual meaning. For example, how the community of network analysis scholars understands its core terms, and how these understandings vary depending on themes, social ties and scholars’ attributes. This enables understanding explanations of how social ties shape perspectives, views, and ideas of actors - and vice versa.

Mixed-method socio-semantic network analysis training offered by this full-day hands-on workshop will introduce participants to: (1) computational word collocation approach, rooted in corpus linguistics, to produce semantic networks of associations between words; (2) descriptive network analysis of social, semantic, and socio-semantic structures; (3) interpretive analysis of texts—to understand these key elements in their textual and relational contexts; (4) basics of multilevel exponential random graph modelling as applied to socio-semantic structures.

The workshop is open to all participants, irrespective of their prior knowledge of descriptive network analysis or modelling. No programming skills are necessary. Participants are welcome to bring small training text datasets of their interest, along with text’s authors and matrices of social ties between them.

Prerequisites: Some experience with R and familiarity with descriptive network concepts and statistical methods for network analysis in the R/statnet platform is expected.  This workshop also assumes familiarity with ERGMs.

Synopsis:

This workshop will provide an introduction to modeling of network dynamics in continuous time using ERGM generating processes (EGPs).  The exponential family random graph models (ERGMs) are a widely used framework for describing graph distributions, allowing flexible and parsimonious specification of both inhomogeneity (i.e., some ties are more likely than others) and dependence (i.e., some ties depend on others).  EGPs complement ERGMs by providing ways of specifying continuous time dynamics whose long-run behavior recapitulates a specified ERGM distribution - thus allowing for dynamic network models that are consistent with specific cross-sectional behavior.  In this session, we will begin with an overview of known classes of EGPs, with an eye to understanding the types of dynamic behavior embodied by each (and where they might be appropriate as empirical models).  We will then discuss simulation and calibration of EGPs within the R/statnet platform, using the ergmgp package.  We will show examples of the use of EGPs to generate dynamics consistent with cross-sectional network data combined with information on tie durations, including continuous time generalizations of the separable temporal ERGMs (STERGMs).  Attendees are expected to have had some prior exposure to R and statnet, and completion of the statnet ERGM workshop session is strongly suggested as preparation for this session (as we will make extensive use of the ergm package).

statnet is a collection of packages for the R statistical computing system that supports the representation, manipulation, visualization, modeling, simulation, and analysis of relational data. statnet packages are contributed by a team of volunteer developers, and are made freely available under the GNU Public License. These packages are written for the R statistical computing environment, and can be used with any computing platform that supports R (including Windows, Linux, and Mac). statnet packages can be used to handle a wide range of simulation and analysis tasks, including support for large networks, statistical network models, network dynamics, and missing data.

The group stage of the FIFA World Cup 2026 concludes during Sunbelt, and there are going to be daily sessions with updates featuring match analyses, civilized discussions, and heated debates.

For those interested in the methods on which these analyses are based, we provide an introduction to some non-standard approaches employing proximity networks, affiliation networks, and passing networks to determine tactical elements such as dynamic player positioning. Many of them have been developed at ETH Zürich and may or may not be used by Team Switzerland.

For those interested, there will also be the opportunity for some hands-on exercises.

The aim of this workshop is to open up new perspectives that make watching world cup matches even more interesting, and more fun. In a companion workshop prior to this one, we provide additional background on soccer analytics more generally.

Prerequisites:  Attendees are expected to have had some prior exposure to R, but extensive experience is not assumed. Familiarity with binary ERG modeling with the R/statnet platform (e.g., from the “Exponential Family Random Graph (ERGM) Modeling with statnet” workshop session) is assumed.

Synopsis:

This workshop session provides a tutorial using statnet software particularly ergm and latentnet  to model social networks whose ties have weights (e.g., counts of interactions) or are ranks (i.e., each actor ranks the others according to some criterion), using latent space models and exponential-family random graph models (ERGMs) generalized to valued ties, and emphasizing a hands-on approach to fitting these models to empirical data.

The ERGM framework allows for the parametrization, fitting, and simulation from models that incorporate the complex dependencies within relational data structures, and provides an extremely general and flexible means of representing them, while latent space models postulate an unobserved social space in which actors are embedded, facilitating principled visualization and group detection. Topics covered within this session include: importing, modifying, and exporting edge values on network objects; an overview of the valued ERGM framework and the notion of reference distribution; an overview of latent space models for social networks; defining and fitting models to empirical data, including ERGM terms meaningful for counts and ranks; interpretation of model coefficients; simulation of networks using these models; and ERGM degeneracy assessment.

statnet is a collection of packages for the R statistical computing system that supports the representation, manipulation, visualization, modeling, simulation, and analysis of relational data. statnet packages are contributed by a team of volunteer developers, and are made freely available under the GNU Public License.  These packages are written for the R statistical computing environment, and can be used with any computing platform that supports R (including Windows, Linux, and Mac).  statnet packages can be used to handle a wide range of simulation and analysis tasks, including support for large networks, statistical networks, valued networks, network dynamics, and missing data.

Artificial Intelligence (AI) is evolving at unprecedented speed, reshaping how we think, work, and collaborate. Once viewed primarily as a novel interface for interacting with computers, AI--especially with the rise of agentic systems and new model architectures--has become a powerful partner for researchers, educators, and practitioners across disciplines.

This workshop introduces participants to core concepts in AI literacy while showcasing emerging trends and practical tools that can enhance everyday academic and professional workflows. Designed for both newcomers and experienced users, the session will highlight how to use AI ethically, creatively, and productively--well beyond generating emails or simple text.

We will explore hands-on examples of leveraging AI for drafting and revising academic documents, supporting code development, and assisting with data analysis through agentic workflows. Participants will also learn about accessible online tools (such as ChatGPT and GitHub integrations) and programming-oriented options in R and Python, including local large language models through platforms like Ollama.

The workshop blends conceptual foundations with live demonstrations, giving attendees a clear overview of what AI can do today--and what the near future may bring. No prior experience with AI is required; curiosity and an interest in expanding your toolkit are all you need.

The netdiffuseR package provides tools for analyzing and simulating the diffusion of innovations and contagion processes on networks. In this workshop, we demonstrate the package’s features by analyzing empirical and simulated data on the diffusion of innovations. The session will include examples of using netdiffuseR jointly with other network analysis packages such as RSiena, statnet, and igraph. NetdiffuseR’s main features are computing network exposure models based on weight matrices (direct ties, structural equivalence, attribute-weighted, etc.), thresholds, infectiousness, and susceptibility. The package works with both static and dynamic networks. Some other capabilities include handling relatively large graphs, simulating networks and diffusion of innovation processes, and visualizing the diffusion of innovations.

While there are no prerequisites, it is suggested that you have a working knowledge of the R programming language. We will use the latest version of the netdiffuseR R package, which can be found on GitHub here: https://github.com/USCCANA/netdiffuseR. During the workshop day, we will provide access to a cloud version of RStudio with the latest version of netdiffuseR, so do not worry if you cannot install the package before the workshop.

This workshop provides a conceptual survey of the major streams of social network theory. Rather than teaching methods or software, it situates foundational network ideas within the broader landscape of social theory. Core mathematical constructs—such as centrality, structural equivalence, and core–periphery structure—are introduced only to clarify the theoretical debates they support, not for hands-on analysis. The workshop is aimed at participants who are new to the network perspective and want a clear map of the field’s main theoretical conversations.

The first part focuses on theories that treat network properties as drivers of outcomes. This includes classic work on social capital (weak ties, structural holes, social resources) and the contagion tradition (interpersonal influence, diffusion of innovation). We examine how centrality, cohesion, and related ideas are interpreted across these literatures, with attention to mechanisms, levels of analysis, and the role of social cognition in shaping perceived networks.

The second part turns to theories that explain the origins of network structure. Here the emphasis is on why networks take the forms they do and why actors come to occupy particular positions. Topics include homophily, preferential attachment, opportunities and constraints in choice, balance theory, and other mechanisms of tie formation.

By the end, participants will have a coherent framework for understanding how social scientists theorize about networks—both as causes of outcomes and as outcomes themselves—and how these lines of thought fit together in the broader social-scientific tradition.

In the interconnected and interdependent world of the twenty-first century, individual and collective outcomes — such as personal and public health, economic welfare, or war and peace — are affected by relationships among individual, corporate, state, and non-state actors. To understand how the world of the twenty-first century operates and make model-based predictions, it is vital to study networks of relationships and gain insight into how the structure of networks affects individual and collective outcomes. To study relationships among attributes under interference, a comprehensive regression framework for dependent predictors, outcomes, and connections is needed. We will provide workshop participants with a hands-on introduction to R package iglm, which implements a comprehensive regression framework for dependent predictors, treatments, outcomes, and connections with important advantages over existing approaches, including interpretability, scalability, and provable theoretical guarantees. We will demonstrate that R package iglm can be used to study spillover in connected populations, including hate speech on social media.

Fritz, C., Schweinberger, M., Bhadra, S., and D.R. Hunter (in press). A regression framework for studying relationships among attributes under network interference. Journal of the American Statistical Association.

A preprint is available at

https://www.tandfonline.com/doi/full/10.1080/01621459.2025.2565851?src=exp-la  

or

https://arxiv.org/abs/2410.07555