Two new publications related to the ongoing COVID-19 pandemic co-authored by CA-SG members from the UKP Lab to appear at the AAAI symposium on AI for the Social Good.
In our publication Data Collection and Annotation Pipeline for Social Good Projects we build a data collection and annotation architecture designed for handling crisis events. Our system is built to deploy rapidly, handle multiple sources, and efficiently process data for annotation. We build collection architecture for Twitter as well as for the collection of news articles from diverse sources. These can then be input into the INCEpTION annotation framework, adapted to facilitate the application of citizen science. As a use case, we explore annotation of COVID-19 related Tweets and news articles for case prediction.
In our work Arguments as Social Good: Good Arguments in Times of Crisis we investigate how natural language methods can provide helpful arguments for decision-makers in crisis such as the COVID-19 pandemic. With the combination of information retrieval and machine learning we detect high quality pro- and con arguments and their trends for a relevant topics. We present a prototype to uncover such decision critical information for a broad range of topics.