Seventh Social Media Mining for Health Applications

The purpose of this competition is to bridge the gap in NLP and social media for COVID-19 research performed in languages other than English. While there has been an increased amount of non-English datasets and tasks using social media, proposed in the last couple of years, there is still a need for different applications on pressing topics. This competition iinvolves identifying personal mentions of COVID-19 symptoms in Spanish language tweets. Note that the annotated set of tweets for this task is a brand new set of curated Spanish-native language tweets and not a translation of the previous English-only data. The proposed task is a three-way classification problem, requiring participants to distinguish personal symptom mentions from other mentions such as symptoms reported by others and references to news articles or other sources.