Social Medium
Social media analysis focuses on understanding and leveraging the vast amount of textual and multimedia data generated on online platforms to address societal challenges and scientific questions. Current research heavily utilizes large language models (LLMs) and transformer-based architectures, coupled with graph neural networks and other machine learning techniques, to detect harmful content (e.g., hate speech, suicide ideation, misinformation), analyze user behavior and sentiment, and predict societal trends. This field is significant for its potential to improve mental health interventions, mitigate the spread of harmful information, and enhance our understanding of social dynamics, impacting both the social sciences and the development of more responsible and ethical online platforms.
Papers
Cross-Linguistic Offensive Language Detection: BERT-Based Analysis of Bengali, Assamese, & Bodo Conversational Hateful Content from Social Media
Jhuma Kabir Mim, Mourad Oussalah, Akash Singhal
The DSA Transparency Database: Auditing Self-reported Moderation Actions by Social Media
Amaury Trujillo, Tiziano Fagni, Stefano Cresci
Contrastive News and Social Media Linking using BERT for Articles and Tweets across Dual Platforms
Jan Piotrowski, Marek Wachnicki, Mateusz Perlik, Jakub Podolak, Grzegorz Rucki, Michał Brzozowski, Paweł Olejnik, Julian Kozłowski, Tomasz Nocoń, Jakub Kozieł, Stanisław Giziński, Piotr Sankowski
PromptMTopic: Unsupervised Multimodal Topic Modeling of Memes using Large Language Models
Nirmalendu Prakash, Han Wang, Nguyen Khoi Hoang, Ming Shan Hee, Roy Ka-Wei Lee