My da|ra Login

Detailed view

metadata language: English

Two Computational Models for Analyzing Political Attention in Social Media

Resource Type
  • Hemphill, Libby (University of Michigan)
  • Schöpke-Gonzalez, Angela M. (University of Michigan)
Publication Date
Funding Reference
  • National Science Foundation
    • Award Number: 1822228
  • Abstract

    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 (, George Washington Libraries (, and the Sunlight Foundation (\#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.

  • Hemphill, Libby, and Angela M. Schöpke-Gonzalez. “Two Computational Models for Analyzing Political Attention in Social Media.” Proceedings of the Fourteenth International AAAI Conference on Web and Social Media (ICWSM 2020) 14, no. 1 (June 2020): 260–71.

Update Metadata: 2020-06-10 | Issue Number: 1 | Registration Date: 2020-06-10

Hemphill, Libby; Schöpke-Gonzalez, Angela M. (2020): Two Computational Models for Analyzing Political Attention in Social Media. Version: 2. ICPSR - Interuniversity Consortium for Political and Social Research. Dataset.