Show simple item record

dc.creatorSmith, Steven T.
dc.creatorKao, Edward K.
dc.creatorMackin, Erika D.
dc.creatorShah, Danelle C.
dc.creatorSimek, Olga
dc.creatorRubin, Donald B.
dc.identifier.citationSteven T. Smith, Edward K. Kao, Erika D. Mackin, Danelle C. Shah, Olga Simek, Donald B. Rubin. Automatic detection of influential actors in disinformation networks. Proceedings of the National Academy of Sciences Jan 2021, 118 (4) e2011216118. DOI: 10.1073/pnas.2011216118
dc.description.abstractThe weaponization of digital communications and social media to conduct disinformation campaigns at immense scale, speed, and reach presents new challenges to identify and counter hostile influence operations (IOs). This paper presents an end-to-end framework to automate detection of disinformation narratives, networks, and influential actors. The framework integrates natural language processing, machine learning, graph analytics, and a network causal inference approach to quantify the impact of individual actors in spreading IO narratives. We demonstrate its capability on real-world hostile IO campaigns with Twitter datasets collected during the 2017 French presidential elections and known IO accounts disclosed by Twitter over a broad range of IO campaigns (May 2007 to February 2020), over 50,000 accounts, 17 countries, and different account types including both trolls and bots. Our system detects IO accounts with 96% precision, 79% recall, and 96% area-under-the precision-recall (P-R) curve; maps out salient network communities; and discovers high-impact accounts that escape the lens of traditional impact statistics based on activity counts and network centrality. Results are corroborated with independent sources of known IO accounts from US Congressional reports, investigative journalism, and IO datasets provided by Twitter.
dc.format.extent10 pages
dc.relation.ispartofCOVID-19 Research
dc.relation.haspartProceedings of the National Academy of Sciences, Vol. 118, Number 4
dc.relation.isreferencedbyProceedings of the National Academy of Sciences
dc.rightsAttribution-NonCommercial-NoDerivs CC BY-NC-ND
dc.subjectCausal inference
dc.subjectMachine learning
dc.subjectSocial media
dc.subjectInfluence operations
dc.titleAutomatic detection of influential actors in disinformation networks
dc.type.genreJournal article
dc.description.departmentStatistical Science
dc.ada.noteFor Americans with Disabilities Act (ADA) accommodation, including help with reading this content, please contact
dc.description.schoolcollegeFox School of Business
dc.temple.creatorRubin, Donald B.

Files in this item


This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial-NoDerivs CC BY-NC-ND
Except where otherwise noted, this item's license is described as Attribution-NonCommercial-NoDerivs CC BY-NC-ND