The workshop will take place on July 19th, 10:00 AM CEST on Zoom
Political science has changed dramatically in the last decade. It has never been easier to retrieve and get access to massive amounts of visual data depicting a wide variety of political events. Further, technological advances have not only allowed researchers, especially in the computer science field, to access that data but also to develop and use methods for the analysis of imagery that were unthinkable a few years ago.
This course provides an introduction to image analysis including core concepts of image structure, feature definition and measurement, and classification. In particular, we will review the intuition, statistical basis and implementation of two methods for the unsupervised and supervised analysis of images: a visual structural topic model based on the Bag of Visual Words, and Convolutional Neural Networks (CNNs). The workshop is divided into two sections: a lecture reviewing theoretical concepts, and an applied part in which we conduct basic classification tasks using Python, OpenCV, and R.
Several of the tools designed to understand visual content rely on the power of computers and machines to achieve their objectives. Thus, students should ideally feel comfortable using R and have had some exposure to other languages like Python, but should minimally be familiar with basic functionality of R.
The workshop is divided into two sections: a lecture reviewing theoretical concepts, and an applied part in which we conduct basic classification tasks using Python, OpenCV, and R.
Prof. Michelle Torres
Michelle Torres is an Assistant Professor at Rice University who specializes in political methodology and political behavior. Her research focuses on making statistical and computer science methods accessible to political scientists. She also develops and applies innovative and rigorous tools to achieve a better understanding of social issues, especially in the fields of political behavior and public opinion. Methodologically, she is interested in computer vision, causal inference and survey methodology. Substantively, she focuses on political communication, participation, and psychological traits.
Image as Data: quantitative image analysis with R and Python (Part I)
Image as Data: quantitative image analysis with R and Python (Part II)
All workshop materials and recording are under Creative Commons Attribution-NonCommercial-ShareAlike 2.0 license. You are free to share — copy and redistribute the material in any medium or format, and adapt — remix, transform, and build upon the material. However, you must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use. You may not use the material for commercial purposes. If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.
- Session slide deck (to be updated)
- Session code notebook