The browser you are using is not supported by this website. All versions of Internet Explorer are no longer supported, either by us or Microsoft (read more here: https://www.microsoft.com/en-us/microsoft-365/windows/end-of-ie-support).

Please use a modern browser to fully experience our website, such as the newest versions of Edge, Chrome, Firefox or Safari etc.

nils holmberg

Nils Holmberg

Senior lecturer

nils holmberg

Computational methods for querying and sampling the Twitter disinformation datasets

Author

  • Nils Holmberg

Summary, in English

This study attempts to apply computational methods to the Twitter Election Integrity Datasets in order to derive a basic descriptive overview of this disinformation data, and to suggest some possible routes for developing these methods to address future research questions. The results indicate substantial variations in tweet frequency over time and geographical regions, as well as differences in relative importance of tweet words across regions. Aggregated tweet measures provide basic descriptive statistics for the datasets.

Department/s

  • Department of Strategic Communication

Publishing year

2020-11-24

Language

English

Document type

Conference - other

Topic

  • Communication Studies

Keywords

  • social media
  • disinformation
  • computational methods
  • text analysis
  • content analysis
  • R package

Conference name

The Carnegie Partnership for Countering Influence Operations

Conference date

2020-11-17 - 2020-11-24

Conference place

United Kingdom

Status

Unpublished

Project

  • Web-based influence campaigns - computational content analysis and user gaze interaction