DETECTING ONLINE PROPAGANDA AND MISINFORMATION

This unique compendium provides a comprehensive overview of the state-of-the-art methods in the extremely 'hot' area of online propaganda detection and monitoring. It discusses the difficulties of developing automated methods and systems for online propaganda and misinformation detection, along with the potential contributions of machine learning techniques.

The presented methods are built upon the latest AI and Natural Language Processing technologies. Case studies refer to recent events such as the COVID-19 pandemic and the Russian-Ukrainian military conflict.

This useful reference text benefits academics, researchers, professionals and graduate students in AI, NLP, machine learning and information sciences.

Contents:

• Detecting and Summarizing Narratives in the Information Environment: A Case Study of Misinformation and Disinformation Campaigns (Emily Saldanha, Anurag Acharya, Mustafa Ocal, Jasmine Eshun, Maria Glenski, and Svitlana Volkova)
• Fake News Detection and Behavioral Analysis: Case of COVID-19 (Chih-Yuan Li, Navya Martin Kollapally, Soon Ae Chun, and James Geller)
• Fake News Detection in Conditions of Limited Data: 'Visual Augmentation' (Nadav Beno, Zeev Volkovich, and Mireille Avigal)
• Pandemic Fake News: Applying NLP to Combat Lies in the Health Domain (Estela Saquete, Miguel Ángel García-Cumbreras, Alba Bonet-Jover, Patricio Martínez-Barco)
• Russia vs. Ukraine: What are the news at the Telegram Front? (Mark Last)
• A Study on Multilingual Detection of Troll Tweets and Accounts (Natalia Vanetik and Marina Litvak)
• Analysis of State-Backed Trolling on Twitter (Lin Miao)
• Russian–Ukrainian War through Telegram: Propaganda Detection, Analysis, and Visualization (Natalia Vanetik, Marina Litvak, and Egor Reviakin)
• Lagging Behind: Challenges of Adapting Automated Propaganda Detection to the Chronological and Geographic Evolution of Language (Veronika Solopova, Robert Nickel, and Dorothea Kolossa)
• War Crime Detection in Videos Using Deep Learning Methods (Yuval Levi, Maxim Katz, Armin Shmilovici, Dmitry Goldgof, and Mark Last)

Readership: Researchers, professionals, academics, graduate students in AI, machine learning and information sciences.