SocialDisNER – Detection of disease mentions in tweets (in Spanish, SMM4H 2022 – Task 10)

SocialDisNER Task overview

About the task

Mining social media content for disease mentions (SocialDisNER) [in Spanish language]. This task will focus on the recognition of disease mentions in tweets written in Spanish after selecting primarily first-hand experience of diseases and other health-relevant content (from patient associations and professional healthcare institutions).

The aim is to use social media as a proxy to better understand societal perception of disease, from rare immunological and genetic diseases such as cystic fibrosis, highly prevalent conditions such as cancer and diabetes, to often controversial diagnoses such as fibromyalgia and even mental health disorders.

Automatic data selection actively retrieved posts with personal messages and from patient associations. Thus, the SocialDisNER shared task will enable training deep learning named entity recognition approaches to detect all kinds of disease mentions in social media, including both lay and professional language.

The Social Media Mining for Health Applications (#SMM4H) Shared Task 2022 invites researchers to develop systems to solve health informatics challenges for social media. The 10th track of the task focuses on the identification of disease mentions in Spanish tweets.

This webpage is devoted to the Spanish part of this multilingual track (i.e. identification of diseases in Spanish tweets enriched with patient and healthcare professional social media content).

There will only be a single sub-track:

  • NER offset detection and classification. Participants must find the beginning and end of disease mentions.

The SMM4H 2022 general webpage can be accessed here.

#SMM4H is held as part of the 29Th International conference on computational linguistics.