Machine learning sentiment analysis, COVID-19 news and stock market reactions.

The recent COVID-19 pandemic represents an unprecedented worldwide event to study the influence of related news on the financial markets, especially during the early stage of the pandemic when information on the new threat came rapidly and was complex for investors to process. In this paper, we investigate whether the flow of news on COVID-19 had an impact on forming market expectations. We analyze 203,886 online articles dealing with COVID-19 and published on three news platforms (MarketWatch.

Global risks, the macroeconomy, and asset prices.

We propose a novel index of global risks awareness (GRAI) based on the most concerning risks-classified in five categories (economic, environmental, geopolitical, societal, and technological)-reported by the World Economic Forum (WEF) according to the potential impact and likelihood occurrence. The degree of public concern toward these risks is captured by Google search volumes on topics having the same or similar wording of that one of the WEF Global Risk Report. The dynamics of our GRAI exhibits several spillover episodes and indicates that concerns on the five different categories of global risks are-on average-highly interconnected.

Google search volumes and the financial markets during the COVID-19 outbreak.

During the outbreak of the COVID-19, concerns related to the severity of the pandemic have played a prominent role in investment decisions. In this paper, we analyze the relationship between public attention and the financial markets using search engine data from Google Trends. Our findings show that search query volumes in Italy, Germany, France, Great Britain, Spain, and the United States are connected with stock markets.

A Matrix-Variate Model for Networks.

Networks represent a useful tool to describe relationships among financial firms and network analysis has been extensively used in recent years to study financial connectedness. An aspect, which is often neglected, is that network observations come with errors from different sources, such as estimation and measurement errors, thus a proper statistical treatment of the data is needed before network analysis can be performed. We show that node centrality measures can be heavily affected by random errors and propose a flexible model based on the matrix-variate distribution and a Bayesian inference procedure to de-noise the data.