A newer version of this project is available. See below for other available versions.

Two Computational Models for Analyzing Political Attention in Social Media

Principal Investigator(s):  View help for Principal Investigator(s) Libby Hemphill, University of Michigan; Angela M. Schöpke-Gonzalez, University of Michigan

Version:  View help for Version V1

Version Title:  View help for Version Title PI, Summary, Citation, and Funding only

Name File Type Size Last Modified

Project Citation: 

Hemphill, Libby, and Schöpke-Gonzalez, Angela M. Two Computational Models for Analyzing Political Attention in Social Media. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2020-03-30. https://doi.org/10.3886/E118569V1

Project Description

Summary:  View help for Summary
Using the Twitter Search API, we collected all tweets posted by official MC accounts (voting members only) during the 115th U.S. Congress which ran January 3, 2017 to January 3, 2019. We identified MCs' Twitter user names by combining the lists of MC social media accounts from the United States project (https://github.com/unitedstates/congress-legislators), George Washington Libraries (https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/UIVHQR), and the Sunlight Foundation (https://sunlightlabs.github.io/congress/index.html\#legislator-spreadsheet).

Throughout 2017 and 2018, we  used the Twitter API to search for the user names in this composite list and retrieved the accounts' most recent tweets. Our final search occurred on January 3, 2019, shortly after the 115th U.S. Congress ended. In all, we collected 1,485,834 original tweets (i.e., we excluded retweets) from 524 accounts. The accounts differ from the total size of Congress because we included tweet data for MCs who resigned (e.g., Ryan Zinke) and those who joined off cycle (e.g., Rep. Conor Lamb); we were also unable to confirm accounts for every state and district.

Twitter prohibits us from sharing the full tweet text, and so we have included tweet IDs when possible.


Funding Sources:  View help for Funding Sources National Science Foundation (1822228)



Related Publications

Download this project

Published Versions

V2 [2020-06-10]

V1 [2020-03-30]

Export Metadata

Dublin Core

DDI 2.5

Report a Problem

Found a serious problem with the data, such as disclosure risk or copyrighted content? Let us know.

This material is distributed exactly as it arrived from the data depositor. ICPSR has not checked or processed this material. Users should consult the investigator(s) if further information is desired.