Prof. Boleslaw K. Szymanski presented the invited talk "Supervised Learning of the Global Risk Network Activation from Media Event Reports" at the Conference on Modelling Methods in Computer Systems, Networks and Bioinformatics in Paris, on Oct. 14, 2019.

Prof. Boleslaw K. Szymanski presented the invited plenary talk "Supervised Learning of the Global Risk Network Activation from Media Event Reports", coauthored by Dr. Xiang Niu and Prof. Gyorgy Korniss, at the Conference on Modelling Methods in Computer Systems, Networks and Bioinformatics in Paris, on October 14, 2019. The conference was organized under the auspices of the French and Polish Foreign Ministries and the French National Academy of Technologies, to mark the 100th Anniversary of French- Polish Scientific Cooperation and was conducted in the Scientific Centre of Polish Academy of Science in Paris opened in 1919 with the involvement of Marie Curie Sklodowska. The talk focuses on the annual reports published by the World Economic Forum (WEF) that define global risks which have the high impact on the world’s economy in the corresponding year. Currently, many researchers analyze the modeling and evolution of risks. However, few studies focus on validation of the global risk networks published by the WEF. In this paper, we first create a risk knowledge graph from the annotated risk events crawled from the Wikipedia. Then, we compare the relational dependencies of risks in the WEF and Wikipedia networks, and find that they share over 50% of their edges. Moreover, the edges unique to each network signify the different perspectives of the experts and the public on global risks. The talk also discusses an auto-detection tool which filters out over 80% media reported events unrelated to the global risks that was developed to reduce the cost of manual annotation of events triggering risk activation. In the process of filtering, our tool also continuously learns keywords relevant to global risks from the event sentences. Using locations of events extracted from the risk knowledge graph, we find characteristics of geographical distributions of the categories of global risks.