Eric C. Vorst: Network Analysis of #APSA2016

Twitter is always an active platform and great networking tool, partiularly during large conferences and events. The APSA 2016 Annual Meeting, located in Philadelphia, PA, was no different with attendees sharing all types of thought on the platform. One of our conference attendees, Eric Vorst, decided to do an analysis of what people were saying and gained quite a bit of interest from the twittersphere. We reached out to Eric to give us some closing analysis of #APSA2016 from a twitter perspective.

ericvorstEric C. Vorst
Network Analysis of #APSA2016

Eric C. Vorst is a PhD candidate in Political Science at the University of Missouri – St. Louis, where he is writing his dissertation on incivility in social media during the 2016 presidential election.  Eric earned his M.A. in political science from University of Missouri – St. Louis, his M.B.A. from Lindenwood University, and his B.A. in English Literature and Philosophy from Central Missouri State University.  His research interests include political communication and behavior, network analysis, and American political development. Eric lives in the St. Louis area with his wife and two children, aged 3 and 5.

Tell us about how you are using this technique in your research.

Vorst: A main focus of my research involves examining how incivility manifests itself in social media.  I’ve looked at this question in some recent conference papers and it serves as the core of my dissertation, which draws upon a data set of approximately 9,000,000 tweets I’ve collected on a daily basis since August, 2015.

I first measure how the use of affective language and extremely uncivil words fluctuates with proximity to a political event.  Next, I analyze network metrics and use visualization tools to observe how neighborhoods of discussions form around messages of different types and with different tones.  This type of approach helps to illustrate the reach and impact incivility has in social media while shedding some light on possible relationships between elite and mass polarization.  I’m excited to have made a few findings that challenge some of the conventional wisdom regarding the negative impact of incivility online.

I’m also applying these methods to study live Twitter streams during the 2016 presidential debates.  It’s a lot of fun being able to collect data, compile it, analyze it, and present it to the public in a matter of minutes.

Network Analysis of #APSA2016 for Entire Conference:

What are some potential areas where this would have an impact?

Vorst: This type of analysis is primarily about relationships between people and groups, which is a characteristic that makes it especially useful in political science.  Specifically, it allows us to identify patterns in the types of discussion occurring within social networks and to observe structural characteristics of the resulting neighborhoods they form.  The exciting part comes when we take into consideration the influence of stimuli external to the social network, as this allows us to draw causal inferences regarding how systems of political communication evolve in response to political events.  This is a major underlying theme in my dissertation and serves as the jumping off point for several of my current research projects.

Basic Network Map of #APSA2016 for the entire conference (3 different zoom levels):

What inspired you to perform the analysis?

Vorst: I attended the 2016 American Political Science Association Annual Meeting as a first-time attendee and a first-time presenter, and really wanted to make the most out of the opportunity I was being given to share my research with our community.  Late on the first night of the conference, I was sitting at the desk in my hotel room thinking of ways I could incorporate some additional interactive elements into my iPoster presentation.  However, I was running into some problems when trying to integrate these changes in a way that worked smoothly.

After few minutes of brainstorming, the realization struck me: I was sitting smack-dab in the middle of the perfect natural experiment. Why not perform a live analysis of what political scientists talk about at a political science convention?  I thought this would be a great way to track different themes and emerging topics on each day of the conference, as well as for the conference as a whole.

I also wanted to make the findings informative, accessible, and timely, so I created YouTube videos detailing my analyses each evening.  This made for several consecutive late nights and early mornings, but in the end I feel the results were well worth the effort.

Network Analyses of #APSA2016 on each individual day:

Day 1 and 2: August 31 – September 1
View also:        Day 3       Day 4       Day 5

Basic maps of each individual day:

What was a surprising finding from your analysis?

Vorst: One especially surprising finding involved how the #APSA2016 network treated political punditry.  Specifically, tweets with politicized content tended to occupy peripheral areas of the social network.  It’s important to note that this does not necessarily indicate such activity was viewed in a substantively negative light.  Rather, it merely suggests that these sorts of discussion did not permeate deeply into the network and, in turn, were less influential when compared to other types of discussions.

It’s also critical to stress that this sort of analysis is non-deterministic.  Rather, it’s based largely upon relationships and, more importantly, the power of strong, interconnected, and influential relationships within a defined system.  These sorts of influential relationships were seen consistently around two popular themes of discussion during the conference involving @womenalsoknow and @monkeycageblog.

Summary Statistics for #APSA2016:

#APSA2016 - Tweet Volume Series (8/31-9/5)
#APSA2016 – Tweet Volume Series (8/31-9/5)

What else would you like people to know about your work?

Vorst: Social media analysis doesn’t just require us to ask new questions, it requires us to ask questions in new ways.  I believe this opens up a great deal of creative possibilities that, if pursued with sufficient academic rigor, have the potential to establish a valuable beachhead in the study of contemporary political communication.  I am honored to be part of a community of scientists from a variety of disciplines who are forging new ground in the pursuit of better understanding the role social media plays in shaping the way people engage in the political process.  I’m very optimistic and excited about what the near future holds for this emerging subfield.

Closer look at specific #APSA2016 tweet content over the entire conference:

I hope my work can provide positive motivation for others like me, who may be working with limited resources in the form of funding and computing power.  I believe there is significant value in looking at things from an alternative perspective, pursuing good questions, and being creative with your available tools. I also believe such an approach often plays a big role in creating opportunities for new discoveries.  If you feel inspired by an interesting idea, why not just dive in and see where it takes you?