Скачать или смотреть Bill Marcellino Detecting and Understanding Conspiracy Theories on Social Media

Conspiracy theories circulated online via social media contribute to a shift in public discourse away from facts and analysis and can contribute to direct public harm. Social media platforms face a difficult technical and policy challenge in trying to mitigate harm from online conspiracy theory language. As part of Google's Jigsaw unit's effort to confront emerging threats and incubate new technology to help create a safer world, RAND researchers conducted a modeling effort to improve machine-learning (ML) technology for detecting conspiracy theory language. They developed a hybrid model using linguistic and rhetorical theory to boost performance. They also aimed to synthesize existing research on conspiracy theories using new insight from this improved modeling effort. This report describes the results of that effort and offers recommendations to counter the effects of conspiracy theories that are spread online.

Bill Marcellino is a senior behavioral scientist in the Washington office of the RAND Corporation, professor of text analytics at the Pardee RAND Graduate School, lecturer at Carnie Mellon’s Institute for Politics and Strategy, and lecturer at Johns Hopkins University. He was trained as a sociolinguist and corpus linguist at RAND he develops analytic toolsets, including RAND-Lex, RAND's proprietary text analytics suite. Marcellino teaches text analytics methods for big datasets (e.g. social media), as well as qualitative research methods. His research focuses on information as a warfighting function, intelligence, military resilience, counter-violent extremism/terrorism, mis/disinformation, and social media as a data source. He has also served as a U.S. Marine tank officer and enlisted rifleman. Marcellino received his Ph.D. in rhetoric from Carnegie Mellon University.