The recent developments in the research area of online misinformation and digital security highlight a significant shift towards leveraging advanced machine learning and natural language processing techniques to combat various forms of digital threats. These include the detection of fake news, pump-and-dump schemes in cryptocurrency markets, media bias, cyber threats on platforms like Telegram, and the presence of hadiths on social media. Additionally, there's a growing focus on improving the fairness and accuracy of rumor detection methods and enhancing the detection of social media bots and smishing attacks. The field is moving towards more sophisticated, multidisciplinary approaches that combine different data analysis techniques to address these challenges effectively.

Noteworthy papers include:

• A novel method for extracting textual features from news articles for misinformation detection, demonstrating the effectiveness of topic features for fake news detection.
• A real-time prediction pipeline for detecting pump-and-dump schemes in cryptocurrency markets, showcasing the use of advanced NLP to classify Telegram messages.
• An experimental framework assessing the generalizability of learning effects in identifying media bias, highlighting the effectiveness of human and AI labels in increasing bias detection.
• A multidisciplinary approach to analyzing Telegram data for early warning of cyber threats, employing neural network architectures and traditional machine learning algorithms.
• A study exploring the presence of hadiths on Arabic social media, providing a methodology for Islamic scholars to validate hypotheses about hadiths on big data.
• A two-step framework addressing the unfairness issue in rumor detection, improving both detection performance and fairness.
• MSM-BD, a multimodal social media bot detection approach using heterogeneous information, introducing cross-modal fusion technology for enhanced detection accuracy.
• A smishing detection model using a content-based analysis approach, achieving high classification accuracies for smishing and ham messages.
• A global comparison of bot and human characteristics on social media, developing a first-principle definition of a social media bot and providing recommendations for their use and regulation.