2nd Annual Conference on Politics and Computational Social Science (PaCSS) 

DATE: Wednesday, August 28
LOCATION: Georgetown University
Georgetown University Hotel & Conference Center, Washington, D.C.

 

CONFERENCE DESCRIPTION

The data and methodologies available to social scientists have exploded with the emergence of vast archives of passive data collection, large scale online experimentation, and innovative uses of simulation.  These data are of a larger magnitude and methods are of a greater computational complexity than approaches that have dominated political science for the last 50 years.

This offers the potential for rich insights into society at scale, while simultaneously introducing new ethical and infrastructural challenges. In parallel, the information and communication technologies that have driven these changes are also driving changes in politics, around the world, that require study.

In order to understand the political world, it is increasingly important to gain access to the political communication and behavior occurring online. This preconference gathering will offer a forum for political science research in this emerging space. Example relevant topics/approaches include:  analysis of social media; text analysis; use of finely granular geographic data; large scale online experimentation.

Scholars from all subfields of political science are welcome, as are researchers in other relevant disciplines, such as computer science, sociology, and physics. The meeting will take place 9am-5pm on Wednesday, August 28th at Georgetown University.

Everyone who wishes to attend should apply. We welcome applications to present, discuss or simply participate. We recognize that strength comes through diversity, and actively seek, welcome, and encourage people with diverse backgrounds, experiences, and identities to apply and attend.

This will be a one day conference with a keynote by Sandra González-Bailón of the University of Pennsylvania. A wide range of subjects for presentations are welcome, including purely methodologically oriented presentations or applications thereof; synthesis/overviews of research; discussions of ethics and/or data infrastructures; and so on. Papers are not required.

 

Register for the conference at our registration page.  Registration is $50 before August 12, 2019 and $100 after that. Seating is limited, so please register early to ensure space.  The conference includes breakfast, lunch, coffee, snacks and a reception with bar and hors d’ oeuvres.

Pew Research Center is pleased to host two parallel training workshops (see tab above, if link does not work in your browser) at their office in downtown D.C. These workshops will focus on two key areas: 1) natural language (NLP) processing techniques and their application to social science questions; and 2) deep learning techniques with applications to image analysis for social scientists. Participants will be given hands-on experience building and training models in these subject areas and will also be able to meet members of Pew Research Center’s Data Labs team. Workshops will run from 2pm to 5pm Tuesday August 27. Light snacks and coffee will be provided. Cost per participant is $25.

PACSS 2019 is sponsored by the McCourt School of Public Policy Data Science for Public Policy Program, the Office of Provost Robert Groves, Georgetown University and Sage Publishing and the Pew Research Center.


Previous Conference: 2018 PaCSS at Northeastern 

Georgetown Programs: Massive Data Institute  |  Master of Science in Data Science for Public Policy

2nd Annual Conference on Politics and Computational Social Science (PaCSS)
Wednesday, August 28, 2019
Georgetown University
Georgetown University Hotel and Conference Center, Washington, DC


Objective

The data and methodologies available to social scientists have exploded with the emergence of vast archives of passive data collection, large scale online experimentation, and innovative uses of simulation. These data are of a larger magnitude and methods are of a greater computational complexity than approaches that have dominated political science for the last 50 years. This offers the potential for rich insights into society at scale, while simultaneously introducing new ethical and infrastructural challenges. In parallel, the information and communication technologies that have driven these changes are also driving changes in politics, around the world, that require study. In order to understand the political world, it is increasingly important to gain access to the political communication and behavior occurring online.

 

Preliminary Conference Program: Wednesday, August 28, 2019

(download PDF version - including speakers)

**Exact times subject to change - please check final schedule to be posted later** 

 

8:45am—9:15am

Welcoming Remarks
 

9:15am—10:30am

Networks  |  Social Media  |  NLP
 

10:30am—10:50am

Break
 

10:50am—12:05pm

Methods in CSS  |  The News  |  Image
 

12:05pm—1:30pm

Lunch & Business Meeting
 

1:30pm—2:45pm

IR  |  Journalism  |  Video
 

2:45pm—3:00pm

Break
 

3:00pm—4:15pm
4:15pm—4:30pm

Break
 

5:30pm—7:00pm

Poster Sessions & Reception

 

 

Breakout Sessions & Speakers

Breakout sessions will offer participants the opportunity to further explore areas most relevant to their work and interests.  

9:15am-10:30am

Networks:

  • Legislative communication style: linking legislators across medium and message
    Rachel Blum, Miami University
  • Network Event History Analysis for Modeling Public Policy Adoption with Latent Diffusion Networks
    Bruce Desmarais, Pennsylvania State University
  • Target Policymaking Under the Frame of Dark Networks: Strengths, Weaknesses and Opportunities
    Joseph Shaheen, George Mason University
  • Failure to Communicate: Individual Reasoning Structure and Deliberative Outcomes
    Sarah Shugars, Northeastern University

Social Media:

  • Knowledge Decays: Temporal Validity in Online Social Science
    Kevin Munger, Penn State University
  • Social Media Markets for Survey Research in Comparative Contexts: Facebook Users in Kenya
    Leah Rosenzweig, Institute for Advanced Study in Toulouse (IAST)
  • The Influencer Ecosystem in the 2018 U.S. Primaries
    Yotam Shmargad, University of Arizona
  • Journalists on Twitter: Self-branding, Audiences, and Involvement of Bot
    Onur Varol, Northeastern University

NLP:

  • A Bayesian Transition Network Topic Model for Inferring Conceptual Networks
    Nick Beauchamp, Northeastern University
  • The Mechanics of Emergent Political Voice
    Amy Magnus, Air Force Institute of Technology  
  • Humans and Machines Learning Together
    Stuart Shulman, Texifter
  • The Digital Pulpit: A Nationwide Analysis of Online Sermons
    Dennis Quinn, Pew Research Center

10:50am-12:05pm

Methods in Computational Social Science:

  • 311: What's Your Emergency?
    Rebekah Getman, Northeastern University
  • Shifting Sands: An Agent-Based Model of Mobilization Against a Central Authority
    Soha Hammam, Claremont Graduate University
  • Analyzing Link Sharing Across Platforms to Study Political Messaging and Ideology
    Joshua Tucker, NYU
  • Event Data with Images
    Zachary Steinert-Threlkeld, UCLA

The News:

  • The Distorting Prism of Social Media: How Online Comments Amplify Toxicity
    Jin Woo Kim, Dartmouth College
  • Affective Polarization in Online Uncivil Comments
    Yujin Kim, University of Texas at Austin
  • Nationalized news: using large-scale collections of close captions text to identify national network stories in local news broadcasts
    Pavel Oleinikov, Wesleyan University
  • Measuring the European public sphere across multiple languages
    Maurits van der Veen, College of William & Mary

Image:

  • Ideological Scaling of Political Images
    Jason Anastasopoulos, University of Georgia
  • Using Computer Vision to Capture the Collective Perception of a Neighborhood
    Laura Nelson, Northeastern University  
  • How do Machines See Gender? Demystifying a machine vision system
    Emma Remy, Pew Research Center
  • Do Women Candidates “Run as Women” Online? An Automated Image and Text Analysis of Campaign Advertising on Facebook and TV
    Jielu Yao, Wesleyan University & University of Iowa

1:30pm-2:45pm

IR:

  • Text-Based Approaches to Analyzing Group Behavior in Conflict Setting
    Margaret Foster, Duke University
  • Where the money blows – Using speeches to identify the effect of Chinese foreign aid on the US-African relationship structure
    Dennis Hammerschmidt, University of Mannheim
  • Detecting Foreign Influence Operations’ Content on Social Media
    Meysam Alizadeh, Princeton University
  • Measuring a Threat Perception: Text Analysis of the Speech Records of the United Nations Security Council, 1994-2019
    Takuto Sakamoto, University of Tokyo

Journalism:

  • Systematic biases in local news search results: an audit study
    Sean Fischer, University of Pennsylvania
  • Can Digital Literacy Save Us from Fake News? Evidence from the U.S.
    Andy Guess, Princeton University
  • Online Information Seeking during the 2018 U.S. Congressional Elections
    Ronald Robertson, Northeastern University
  • How Does the Media Environment Affect Readership? Evidence from an App Patient-Preferred Trial in Italy
    Alessandro Vecchiato, Stanford

Video:

  • Automated Coding of Political Campaign Advertisement Videos: A Validation Study
    Wonjoon Hwang, Harvard University
  • Comparing Human and Machine Classification of Written and Video Records of Parliamentary Debates
    Christopher Cochrane, University of Toronto  
  • How Online Propaganda Radicalizes Foreign Citizens
    Tamar Mitts, Columbia University
  • Mapping Extremist Networks with Visual Imagery
    Rob Williams, UNC Chapel Hill

3:00pm-4:15pm

Attitudes & Beliefs:

  • Religiosity and Public Policy in Congress: Analyzing the partisan dimensions of legislators’ religious rhetoric
    Sarah Dreier, University of Washington
  • Gender Norms and Violent Behavior in a Virtual World
    Eric Dunford, Georgetown University
  • Ecologies of Online Contention: From Hate to Health
    Neil Johnson, George Washington University
  • Can Celebrities Reduce Prejudice? The Effect of Mohamed Salah on Islamophobic Attitudes and Behaviors
    Alexandra Siegel, Stanford University

Campaigns:

  • Downsian Convergence on Non-Policy Issues: Evidence from Campaign Manifestos at French Legislative Elections
    Caroline Le Pennec, University of California, Berkeley
  • The Supply and Demand of Fact v. Opinion in Presidential Tweets
    Stan Oklobdzija, Claremont McKenna College
  • From Home Base to Swing States: Spatio-temporal Analysis of Political Advertising Strategies
    Piotr Sapiezynski, Northeastern University
  • Pandering Politicians: Ideological Changes from Primary to General Elections
    Ye Wang, New York University

Machine Learning:

  • Automated Visual Clustering: A Technique for Image Corpus Exploration and Annotation Cost Reduction
    Kevin Aslett, University of Washington
  • Active Learning for Probabilistic Record Linkage
    Ted Enamorado, University of North Carolina at Chapel Hill  
  • Data-driven causal inference for applications in political economy
    Daniel Malinsky, Johns Hopkins University
  • A Computational Social Science Approach to Financial Regulation
    Sharyn O'Halloran, Columbia University
Updates posted when available.

Poster Sessions

Poster sessions will offer participants the opportunity to interact with authors and discuss their research without time constraints.  

  • Dynamical equilibria in iterative voting games
    Samuel Baltz, University of Michigan
     
  • Character as a Network of Spreading Activation
    Bob Boynton, University of Iowa  
  • News by Popular Demand: Ideology, Reputation, and Issue Attention in Social Media News Sharing
    Ernesto Calvo, University of Maryland  
  • Data Science and Analytics to Explore the LGBTQ+ Experience
    Kelsey Campbell, Gayta Science  
  • A taxonomy of Disinfo Wars
    Hossein Derakhshan, MIT Media Lab  
  • Ideological alignment of attention clusters
    Amruta Deshpande, Graphika Inc.  
  • Emotion and Reason in Political Language
    Gloria Gennaro, Bocconi, NYU  
  • The Politics of Interruption in Ecuador
    Analia Gomez Vidal, University of Maryland, College Park  
  • "I found this on Facebook/Twitter": Use of Social Media as Source
    Naeemul Hassan, University of Maryland  
  • Understanding Coordination Patterns of Disinformation Campaigns in Seven Countries
    Franziska Keller, Hong Kong University of Science and Technology  
  • Language and tone in human rights promotion: friends and foes in the Universal Periodic Review
    Gino Pauselli, University of Pennsylvania  
  • Layering Access to Reentry Programs with Agent-Based Modeling (LARPing with ABM)
    Dwayne Smith , George Mason University  
  • Simulating elections: a multi-agent system of strategic electors and strategic parties to assist election forensics
    Fabricio Vasselai, University of Michigan  
  • Tweet for hate? Towards an assessment of the pattern of anti-sentiment towards economic migrants and refugees in Eastern and Southern Africa
    Soazic Elise Wang Sonne, University of Oxford/ Max Planck Institute (MPIDR)  
  • A Network Theory of the Ruling Coalition
    Omer Faruk Yalcin, Penn State University  
  • Understanding the dynamics of global climate change rhetoric through text analysis
    Bi Zhao, Purdue University

2nd Annual Preconference on Politics and Computational Social Science (PaCSS) at the McCourt School of Public Policy, in conjunction with the Data Science for Public Policy Program<.

Wednesday, August 28, 2019, Georgetown University, Washington DC

Workshops at Pew

Pew Research Center is pleased to host two parallel training workshops on Tuesday August 27 at their office in downtown D.C. These workshops will focus on two key areas: 1) natural language (NLP) processing techniques and their application to social science questions; and 2) deep learning techniques with applications to image analysis for social scientists. Participants will be given hands-on experience building and training models in these subject areas and will also be able to meet members of Pew Research Center’s Data Labs team. Workshops will run from 2pm to 5pm Tuesday August 27. Light snacks and coffee will be provided. Cost per participant is $25.

Natural Language Processing (NLP) 

This workshop will offer a soup-to-nuts overview of text-as-data methods for political, social, and policy applications using R, split into two sections. The first section will provide both a practical and theoretical introduction to text-as-data approaches including: how to acquire text data, how to clean and organize text data, and challenges and considerations for working with text sources in combination with other types of data. In particular, the first section will introduce dictionary-based techniques (and discuss their pitfalls and alternatives), as well as visualization strategies for summarizing corpora. The second section will focus on more advanced approaches to evaluating text data, including clustering, topic modeling, and word embeddings. 

Sarah BouchatThis workshop will be led by Sarah Bouchat. Bouchat is an Assistant Professor at Northwestern University, and is core faculty in the Political Science Department as well as the Institute for Complex Systems (NICO). At Northwestern, Bouchat teaches courses in machine learning, text-as-data, Bayesian statistics, and research design for social science. They completed their PhD in the Department of Political Science at the University of Wisconsin–Madison in 2017. With research interests in political methodology, comparative political economy, and authoritarian politics with a regional focus on Southeast Asia, Bouchat's research has focused on elicited priors, as well as machine learning and Bayesian statistical applications for the study of low information, authoritarian regimes like Myanmar.

Image Processing

As the volume and accessibility of media content has increased in recent years, computational methods for content analysis at scale have gained popularity. Until recently, these studies limited their use of computational methods to text analysis. As a result, current innovations and developments in the field of deep learning for computer vision, or automated image content analysis, remain unfamiliar and inaccessible for most social science researchers. This workshop aims to bridge this gap, by providing a brief theoretical background along with hands-on experience with deep learning for image analysis. The focus of the workshop is on feature extraction and image classification. It will be of particular interest to scholars studying social media or any domain where large numbers of images (e.g. tens of thousands or more) need to be labeled. It also serves as a useful introduction for scholars interested in studying video data. The first part of the workshop introduces deep learning and Convolutional Neural Networks (CNNs). The second part is a hands-on tutorial using Python. It will cover how to 1) use pre-trained CNNs to extract features of interest from an image (e.g. identifying particular objects), and 2) how to train CNNs to classify images into user-determined categories using labeled examples. Experience with Python will be helpful but is not required.

Nora Webb Williams

This workshop will be led by Nora Webb Williams.  Williams is a PhD Candidate in the University of Washington Department of Political Science studying comparative politics, methods, and political economy. Her dissertation research addresses economic resilience and the long-term impacts of colonialism on social trust, with a regional focus on the former Soviet Union. She also writes about the impact of social media and images on protest mobilization, examining diverse cases such as the 2010 revolution in Kyrgyzstan and the Black Lives Matter movement in the United States. Her primary methodological interest is in images as data for social science research, with related interests in machine learning, text as data, and causal inference. Notable experiences outside of the university setting include serving as a Peace Corps volunteer in Kazakhstan and Liberia. Her work has been published or is forthcoming in Political Research Quarterly, Central Asian Survey and Nationalities Papers.

Organizing Committee Members:

Michael Bailey
Georgetown University

David Lazer
Northeastern University

Sarah Shugars
Northeastern University

Hotel Information

Conference participants are welcome to stay at any hotels in the area. The event will be held at the Georgetown University Hotel and Conference Center. The Hotel is located on the Georgetown University campus.

Getting to Campus

If you are driving to campus, you should plan to park at the Southwest Garage located at the bottom of Kennedy Hall. You should use 3611 Canal Road NW as the address when mapping directions in GPS. It is important to note that this garage is cash only. You can find additional directions about driving to campus here and additional information about parking here. We will share additional information about transportation reimbursements at the conference. 

If you are taking a taxi or ride share vehicle, it is easiest to get dropped off at the Main Gates of the University, located at the intersection of 37th and O Streets NW. The University does not allow taxis, Ubers, Lyfts, etc. on campus, so you should not use the parking garage address or any other campus location as a drop off spot. 

Wifi Access
In order to access wifi on campus, switch to the GuestNet wireless network.
Read more about Georgetown Wifi Services.

Campus Map
(click to view a PDF map)

GU Campus Map