Natural language processing and financial markets: semi-supervised modelling of coronavirus and economic news (SUERF)

This paper investigates the reactions of US financial markets to press news from January 2019 to 1 May 2020. To this end, we deduce the content (topic) and sentiment (uncertainty) of the news by developing apposite indices from the headlines and snippets of The New York Times, using unsupervised machine learning techniques. In particular, we arrive at the definition of a set of daily topic-specific uncertainty indices. These indices are then used to find explanations for the behaviour of the US financial markets. In substance, we find that two topic-specific uncertainty indices, one related to COVID-19 news and the other to trade war news, explain the bulk of the movements in the financial markets from the beginning of 2019 to end-April 2020. Moreover, we see that the volatility of the returns of the S&P 500 is positively affected by an increase in the ‘coronavirus’ and ‘trade war’ uncertainty indices.