Register Now

Register by 11:59 PM ET, Thursday, August 8, 2024

Become a Teaching Assistant for this program!

Apply Here

Academy Overview

The MIDAS-ICPSR Social Data Science Summer Academy is a week-long hybrid program hosted collaboratively by the Michigan Institute for Data Science (MIDAS) and the Inter-university Consortium for Political and Social Research (ICPSR). Designed for both ICPSR members and University of Michigan researchers, this intensive academy will provide a thorough and practical overview of essential data science techniques and how they can be applied to advance social science research.

Led by globally leading experts in data science and social science, sessions will be offered simultaneously virtually by Zoom and in-person at the University of Michigan campus. Through lectures, hands-on workshops, example applications, and group discussions, participants will develop core competencies in areas such as machine learning, statistical modeling, data visualization, textual analysis, and more.

Additionally, instructors will highlight cutting-edge methods like deep learning and neural networks tailored to social science research questions and data. Specific applications covered will align with research interests of participants, exploring relevant case studies and projects across the social sciences and beyond, in domains like political science, sociology, public health and epidemiology, communications, economics, and more.

Academy Details

Outcomes

Participants will walk away with the knowledge and tools to implement data science approaches in their own work as well as connections to a community of peers for continued learning, including access to all Zoom-session recordings and materials through December 31.

Whether hoping to upskill methodological toolkits or tap into emerging techniques in the field, this immersive academy will provide social scientists and related researchers and applied practitioners with the foundations to advance their study and understanding of the social world through data science.

Tuition Cost

  • Current University of Michigan faculty, researchers, post-docs, and PhD students are eligible for a University of Michigan Provost-subsidized registration fee of $100.
  • Other ICPSR Members: $1800
  • ICPSR Non-members: $3300

Who Should Attend

Designed for both ICPSR members and University of Michigan researchers, this intensive academy will provide a thorough and practical overview of essential data science techniques and how they can be applied to advance social science research.

This workshop is limited to faculty, postdoctoral researchers, PhD students, and applied practitioners. Current Master’s and undergraduate students are not eligible to participate.

Prerequisites

  • Participants are expected to bring a laptop with administrative rights to download software that will be used for the workshop.

Location

TBA – In-Person or Online*

*University of Michigan-affiliated participants are expected to attend the workshop in-person.

Curriculum Overview (tentative)

Monday and Tuesday: We will introduce foundational concepts and mathematical intuition for machine learning, and an introduction to Python for data analysis. Then, we’ll introduce the data science research workflow and use examples in social science research to put data science ideas and practices together into a workflow.

Wednesday: We will introduce statistical and machine learning tools that enable the systematic analysis of text, focusing on natural language processing and Large Language Models. The session will combine traditional instruction with practical coding exercises during in-class sessions.

Thursday: We will focus on image data in social science research with lectures and coding sessions. Specific topics include: 1) Image basics: pixels, features, and image structure. 2) From text to images: similarities and differences. 3) Classifying images. 4) Big of Visual Words. 5) Further research, resources and challenges. 

Friday: Network analysis is a foundational methodology in social data science, with important advances occurring each year, and in many disciplines. We will introduce modeling and prediction with network data, focusing on: 1) Statistical models for networks; 2) Latent variables and measurement with network data; 3) Link prediction; 4) Graph machine learning. The day will include lectures, discussion of published application examples, and tutorials that involve open source software and real-world data.

Instructors

Bruce Desmarais

DeGrandis-McCourtney Early Career Professor in Political Science, Director of the Center for Social Data Analytics, and an Affiliate of the Institute for Computational and Data Sciences at Penn State University.

Edgar Franco-Vivanco

Edgar Franco Vivanco

Assistant Professor of Political Science, College of Literature, Science, and the Arts and Faculty Associate, Center for Political Studies, Institute for Social Research

Elle O'Brien

Elle O’Brien

Lecturer III in Information and Research Investigator, School of Information

Michelle Torres

Assistant Professor in the Department of Political Science at University of California, Los Angeles

Co-Organizers

ICPSR logo

Questions?

Contact Faculty Training Program Manager, Kelly Psilidis at psilidis@umich.edu