The first CLARIN Café: CLARIN in times of Corona took place Wednesday the 27 May and was organised by CLARIN ambassador prof. Toine Pieters from Utrecht University.
This CLARIN Café aimed to be an informal get-together for researchers to exchange Corona-related research ideas and results, and a platform for discussion and inspiration on the possibilities of the CLARIN infrastructure to support such research.
The first invited speaker was Shihan Wang, who talked about social media data during the Corona crisis, in particular how they can help detect temporal, national, and public sentiment during the time of Corona. In the discussion session with Aleksei Kelli, chair of the CLARIN Legal and Ethical Committee, GDPR issues related to the use of Twitter data for the analysis of public sentiment were addressed. Shihan Wang was particularly interested in using the CLARIN infrastructure for transnational comparative research.
The second speaker, Roland Geraerts showcased the relevance of his work on crowd behaviour during social distancing times. At the café, he performed a real-time simulation of crowd behaviour to estimate the impact of the 1.5-meter social distancing on the movement of crowds; a very insightful perspective of the “new normality” we are living in. The presentation was followed by a discussion session with Arjan van Hessen, member of the CLARIN User Involvement Committee, who posed questions related to the use of real-life-data for the creation of the crowd simulation.
The last speaker Thomas Schoegje talked about how search engines can find meaningful scientific answers to questions about the Coronavirus. The talk was followed by a discussion session with Bente Maegaard, Chair of the CLARIN Knowledge Sharing Infrastructure Committee, who addressed questions of multilinguality in information retrieval related to COVID-19 datasets.
During the café CLARIN’s initiatives related to corona virus were presented. CLARIN is extending the collection of parliamentary data sets with curated collections of recent parliamentary debates about the corona dynamics, and will support the development of tools for detecting mis- and disinformation to be applied to news sources and social media platforms.
An overview of COVID related data collections, infrastructural support and NLP tools that can be helpful for the study of COVID-19 related phenomena can be found at the CLARIN & COVID-19 page.