Featuring: Eugeniu Costechi (Publications Office of the European Union)
On 14 May, the EU Datathon 2021 hosted their third webinar featuring Eugeniu Costechi who presented the Euro-COVID19 dataset for Natural Language Processing (NLP). This dataset can be used for tackling all challenges of the EU Datathon.
Eugeniu talked about the SemCovid project, funded by the Publications Office of the European Union. The project publicly provides the open-source code and the data to establish a semantic mapping of the EU and its Member States in responding to the pandemic. In doing so, the project aims to answer: “How do the COVID-19 measures compare between Member States and across the EU in terms of issues they address, and the degree of content similarity?”. In addition, the project aims to pinpoint what the emerging topics currently are, how they evolved over time, and what actions are undertaken by which actors.
The Euro-COVID19 dataset includes information of COVID-19 measures and metadata which enables users to answer the aforementioned questions, by methods such as text mining and NLP.
Curious to learn more? Have a look at the recording and stay tuned for upcoming last webinar with the Directorate-General for Justice and Consumers (DG JUST).