An annotated Avian Influenza dataset from two event-based surveillance systems

Résumé 0

These dataset concerns Avian Influenza (AI) data from news items (articles) collected by two event-based surveillance systems; HealthMap and PADI-Web published between 2018 and 2019. Collected articles were manually annotated by relevance for epidemic intelligence purposes. A relevant article reports one epiemiological avian influenza event (outbreak) or more while, an irrelevant article is related to sanitary/political/economic measures or mentions another disease. This dataset can be used to train or evaluate classification approaches and classify these AI events by relevance. The structure of the dataset is as follow: EBS: name of the event-based surveillance systems that detected the event (HealthMap or PADI-Web in this case) Country: Name of the country where the event happened Place_name: Name of the administration, city or district where the event happened Disease_name: Name of the disease that is reported in the article Species_name: Name of the affected host that is reported in the article Alert_id: Event identifier Source: Name of the news outlet reporting the article. href: URL information of the article reporting the considered event. Note that multiple article can report same event. Issue_date: Date of the article publication Manualclass: Manual classification (Relevant or Irrelevant) lon: Longitude for the spacial entity lat: Lattitude fot the spacial entity