|Publication type||Research Report|
|Number of pages||67|
Detecting Malign or Subversive Information Efforts over Social Media, Scalable Analytics for Early Warning a research conducted within the International Security and Defense Policy Center of the RAND National Defense Research Institute.
This publication outlines the need for scalable analytic means to detect malign or subversive information efforts, lays out the methods and workflows used in detection of these efforts, and details a case study addressing such efforts during the 2018 World Cup. This information has operational relevance to the U.S. government, including the Department of Defense, and its allies tasked with agile detection and opposition of state-sponsored disinformation. It may also benefit researchers with an interest in going beyond post hoc human recognition of campaigns and social media companies interested in preventing their platforms from being co-opted by malign state actors.
The United States has a pressing capability gap in its ability to detect malign or subversive information campaigns in time to respond to them before these efforts substantially influence the attitudes and behaviors of large audiences. While there is ongoing research attempting to detect parts of such specific campaigns (e.g., compromised accounts, “fake news” stories), this report addresses a novel method to detect whole efforts.
As a proof of concept to detecting malign or subversive information campaigns over social media, we adapted an existing social media analysis method, combining network analysis and text analysis to map out, visualize, and understand the communities interacting on social media. This method works at scale. It allows analysts to look for patterns of disinformation in data sets that are too large for human qualitative analysis, reducing an enormous data set into smaller/denser data sets wherein a faint disinformation signal can be detected.
We examined whether Russia and its agents might have used the Russian hosting of the 2018 Fédération Internationale de Foot-ball Association (FIFA) World Cup as a launching point for malign and subversive information efforts. To do so, we analyzed approximately 69 million tweets—in English, French, and Russian—about the 2018 World Cup in the month before and the month after the Cup. We were able to identify what appear to be two distinct Russian information efforts, one aimed at Russian-speaking audiences, and one at French-speaking audiences:
1) Russian-language efforts were characterized with relatively high confidence as likely including state-sponsored actions. These efforts were focused within two communities, and they centered on validating the Russian annexation of Crimea and justifying possible further military action against Ukraine;
2) French-language efforts were also focused within two communities. One of these we rated with high confidence and the other with low confidence, as state sponsored. In one community these efforts centered on stoking right-wing extremism and populist resentment, and in the other community they centered on encouraging left- and right-wing extreme positions on immigration.
William Marcellino, Krystyna Marcinek, Stephanie Pezard and Miriam Matthews, RAND Corporation, National Defense Research Institute, Detecting Malign or Subversive Information Efforts over Social Media, Scalable Analytics for Early Warning (2020)
Click on a star to rate it!
Average rating / 5. Vote count:
No votes so far! Be the first to rate this post.