There is a pressing need to exploit health-related content from social media, a global source of data where key health information is posted directly by citizens, patients and other healthcare stakeholders. Use cases of disease related social media mining include disease outbreak/surveillance, mental health and pharmacovigilance. Current efforts address the exploitation of social media beyond English. The SocialDisNER task, organized as part of the SMM4H 2022 initiative, has applied the LINKAGE methodology to select and annotate a Gold Standard corpus of 9,500 tweets in Spanish enriched with disease mentions generated by patients and medical professionals. As a complementary resource for teams participating in the SocialDisNER track, we have also created a large-scale corpus of 85,000 tweets, where in addition to disease mentions, other medical entities of relevance (e.g., medications, symptoms and procedures, among others) have been automatically labelled. Using these large-scale datasets, co-mention networks or knowledge graphs were released for each entity pair type. Out of the 47 teams registered for the task, 17 teams uploaded a total of 32 runs. The top-performing team achieved a very competitive 0.891 f-score, with a system trained following a continue pre-training strategy. We anticipate that the corpus and systems resulting from the SocialDisNER track might further foster health related text mining of social media content in Spanish and inspire disease detection strategies in other languages.

Detection of occupations in texts is relevant for a range of important application scenarios, like competitive intelligence, sociodemographic analysis, legal NLP or health-related occupational data mining. Despite the importance and heterogeneous data types that mention occupations, text mining efforts to recognize them have been limited. This is due to the lack of clear annotation guidelines and high-quality Gold Standard corpora. Social media data can be regarded as a relevant source of information for real-time monitoring of at-risk occupational groups in the context of pandemics like the COVID-19 one, facilitating intervention strategies for occupations in direct contact with infectious agents or affected by mental health issues. To evaluate current NLP methods and to generate resources, we have organized the ProfNER track at SMM4H 2021, providing ProfNER participants with a Gold Standard corpus of manually annotated tweets (human IAA of 0.919) following annotation guidelines available in Spanish and English, an occupation gazetteer, a machine-translated version of tweets, and FastText embeddings. Out of 35 registered teams, 11 submitted a total of 27 runs. Best-performing participants built systems based on recent NLP technologies (e.g. transformers) and achieved 0.93 F-score in Text Classification and 0.839 in Named Entity Recognition. Corpus: https://doi.org/10.5281/zenodo.4309356

The global growth of social media usage over the past decade has opened research avenues for mining health related information that can ultimately be used to improve public health. The Social Media Mining for Health Applications (#SMM4H) shared tasks in its sixth iteration sought to advance the use of social media texts such as Twitter for pharmacovigilance, disease tracking and patient centered outcomes. #SMM4H 2021 hosted a total of eight tasks that included reruns of adverse drug effect extraction in English and Russian and newer tasks such as detecting medication non-adherence from Twitter and WebMD forum, detecting self-reported adverse pregnancy outcomes, detecting cases and symptoms of COVID-19, identifying occupations mentioned in Spanish by Twitter users, and detecting self-reported breast cancer diagnosis. The eight tasks included a total of 12 individual subtasks spanning three languages requiring methods for binary classification, multi-class classification, named entity recognition and entity normalization. With a total of 97 registering teams and 40 teams submitting predictions, the interest in the shared tasks grew by 70% and participation grew by 38% compared to the previous iteration.