Workshops

We are pleased to offer 4 workshops, to be held online from Tuesday, 6/15 to Friday, 6/18. Each workshop will run 1-4pm Eastern U.S. The basic information can be found below. To attend the workshops, please register by Friday, 6/11. The registration form can be accessed here.

WORKSHOPS

  • Title: Network Visualization with R

Trainer: Katherine Ognyanova (Rutgers University)

Date & Time: 1-4pm, June 15th, 2021

Materials: https://kateto.net/polnet2021

Description: This workshop will cover network visualization using the R language for statistical computing (cran.r-project.org) and RStudio (rstudio.com). Participants should have some prior knowledge of R and network concepts. The workshop will provide a step-by-step guide describing through series of examples the path from raw data to graph visualization in the igraph and Statnet frameworks. The advanced portion of the workshop will touch on dynamic visualization for longitudinal networks and combining networks with geographic maps. We will also discuss ways of converting graphs in R to interactive JavaScript/3D-based visualizations for the Web.

Instructor Bio: Katherine (Katya) Ognyanova is an Associate Professor at the School of Communication and Information, Rutgers University. She studies the social factors affecting political behavior, confidence in institutions, information exposure, and public opinion formation. Her methodological expertise is in computational social science, network analysis, and survey research. Ognyanova is also one of the lead researchers on The COVID States Project (covidstates.org), a large multi-university initiative exploring the social and political implications of COVID-19. You can visit Katya’s website at www.kateto.net or follow her on Twitter at @Ognyanova.

---------------------------------------------------------------------------------------

  • Title: Exponential Family Random Graph Modeling (ERGMs) with R

Trainer: Ted Hsuan Yun Chen (University of Helsinki)

Date & Time: 1-4pm, June 16th, 2021

Materials: https://tedhchen.com/ERGMintro/

Description: How do we explain the formation of ties on a network? Beyond actor- and dyad-level factors, network effects such as reciprocity often play a role. This workshop introduces the exponential random graph model (ERGM) that lets us statistically study how network ties are formed. The workshop is also a tutorial on how to fit these models in R. In the first part of the workshop, we will discuss the logic of using local network configurations to study social and political processes in a networked system. Next, we will look at how to conduct inferential statistical analysis of these processes using the ERGM framework. This portion of the workshop will be heavily integrated with a tutorial on how to run these models in R using the statnet suite of packages, and will be designed to allow participants to follow the tutorial on their own computers. A basic understanding of social network analysis and a working knowledge of R is assumed.

Instructor Bio: Ted Hsuan Yun Chen is a Postdoctoral Researcher jointly appointed in the Faculty of Social Sciences, University of Helsinki and the Department of Computer Science, Aalto University. His primary research agenda focuses on the social and political consequences of climate change, and efforts to stem these negative and often conflictual outcomes. Methodologically, he is interested in developing computational and network approaches for studying sociopolitical phenomena as complex systems. His work on network analysis has been published in outlets such as Political Analysis and Political Science Research & Methods.

---------------------------------------------------------------------------------------

  • Title: Methods at the Intersection of Network and Text Analysis

Trainer: Sarah Shugars (New York University)

Date & Time: 1-4pm, June 17th, 2021

Materials: https://github.com/sshugars/PolNet2021

Description: This workshop will introduce participants to approaches for analyzing text-as-networks, covering both conceptual foundations and practical applications. Particular focus will be given to the scope of researcher modeling choice and the challenges of inferring network structure(s) from text. The workshop will also include hands-on coding activities, demonstrating a range of strategies for inferring and interpreting textual network structure. No prior training in text or network methods is required. The coding elements of the workshop will be offered in Python, and participants are encouraged to follow along on their own computers. Those with basic familiarity of Python syntax and data structures will get the most out of the coding portion of the workshop, but anyone who is interested in developing their conceptual understanding of network and textual methods is welcome to attend.

Instructor Bio: Dr. Sarah Shugars is a computational political scientist, developing new methods in natural language processing, network analysis, and machine learning in order to examine questions of how people express their political views, reason about political issues, and engage with others around matters of common concern. They are currently a Faculty Fellow at NYU’s Center for Data Science (CDS) and an affiliated Research Fellow in the School of Media and Public Affairs at George Washington University. They received their Ph.D. from Northeastern’s Network Science program in Spring 2020.

---------------------------------------------------------------------------------------

  • Title: Introduction to Latent Factor Models for Networks

Trainer: Shahryar Minhas (Michigan State University)

Date & Time: 1-4pm, June 18th, 2021

Materials: https://s7minhas.com/polnet21_lfm_wkshp.zip

Description: This workshop will provide an introduction to latent space models in general with a particular focus on Peter Hoff’s latent factor model. We will talk about how it can be used for inference when dealing with dyadic data and how it can be used to obtain lower dimensional representations of how actors relate to one another. Both these topics will be handled in the context of applied examples from political science. Last, we’ll discuss the extent to which AME can be used for longitudinal networks and caveats to keep in mind when using it for inferential tasks.

Instructor Bio: Shahryar Minhas is an Assistant Professor at Michigan State University and received his Ph.D. in Political Science from Duke University in 2016. Generally, his research program stems from his training in international relations and political methodology with a focus on how to study social systems in which the actions of actors are interdependent. His methodological focus falls under the heading of network science, but his two specific areas of interest are: how can we do inference in the presence of interdependent observations and how can we build on network properties to learn about the underlying structure of a social system. His research has appeared in the Journal of Politics, Political Analysis, Network Science, Social Networks, among other journals.