2025 DDDSM

The COVID-19 pandemic has accelerated the shift from traditional epidemiological surveillance to digital disease detection systems, largely driven by the widespread adoption and utilization of social media platforms. Conventional surveillance methods rely heavily on clinical data and laboratory confirmation, often resulting in delayed alerts and responses to emerging outbreaks. In contrast, digital disease detection leverages advanced computational methodologies, including natural language processing (NLP) and large language models, to rapidly analyze extensive social media datasets, offering early indicators of health crises, often weeks ahead of traditional methods. 

Recent global health events, notably the Mpox and COVID-19 outbreaks, have underscored the critical role that social media platforms can play in disease surveillance. Platforms such as Twitter have demonstrated the ability to track real-time public health trends, monitor public sentiments, and disseminate critical health information effectively. Furthermore, the incorporation of artificial intelligence (AI) and machine learning techniques into disease detection has proven effective in identifying diverse health conditions, including mental health disorders. Building on the success of the initial DDDSM workshop at the International Joint Conference on Natural Language Processing (IJCNLP) held in Taipei, Taiwan in 2017, we invite submissions for the DDDSM 2025 workshop. This workshop aims to continue exploring how advanced computational methods applied to social media data can enhance early outbreak detection, inform public health responses, and address the ethical considerations involved in digital surveillance.