The aim of the Social Media Mining for Health Applications and Health Real-World Data (#SMM4H-HeaRD) shared tasks is to fos- ter the development and evaluation of natural language processing, machine learning, and artificial intelligence methods for analyzing health-related text from social media and other real-world data sources. For the 11th iteration, held online and co-located with ACL 2026, the workshop continued the expanded #SMM4H- HeaRD platform initiated in 2025, broaden-ing its scope beyond social media to include additional health real-world data sources such as clinical narratives and biomedical literature. The 8 shared tasks covered diverse data sources, health domains (e.g., adverse drug events, insomnia, influenza vaccine effectiveness, cancer staging, substance use), and task formulations (e.g., classification, named entity recognition, span extraction, and text generation). In total, 110 teams registered, representing 31 countries. In this paper, we present an overview of the datasets, participant systems, and performance results, providing insights into current methods for mining social media and health real-world data for biomedical and clinical applications.

This paper provides an overview of Task 2 from the Social Media Mining for Health and Health Real-World Data (#SMM4H-HeaRD) 2026 Workshop and Shared Tasks, which focused on the detection of insomnia in clinical notes derived from the MIMIC-III dataset. The task consisted of two subtasks: binary text classification to determine whether a patient is likely experiencing insomnia (Subtask 1), and multi-label classification combined with character-level evidence extraction to identify supporting evidence for specific insomnia crite- ria (Subtask 2). Eight teams participated, using approaches ranging from large language model (LLM) prompting and fine-tuned encoder mod- els to hybrid rule-based pipelines. Results demonstrated that structured LLM pipelines with deterministic post-processing achieved the strongest overall performance, while character-level span extraction remained substantially harder than classification across all systems. These findings highlight both the promise of NLP for identifying underdiagnosed conditions in electronic health records and the ongoing difficulty of producing interpretable, evidence-grounded clinical predictions.