Analyzing the emotional impact of COVID-19 with Twitter data: Lessons from a B-VAR analysis on Italy.

The novel coronavirus 2019 revolutionized the way of living and the communication of people making social media a popular tool to express concerns and perceptions. Starting from this context we built an original database based on the Twitter users' emotions shown in the early weeks of the pandemic in Italy. Specifically, using a single index we measured the feelings of four groups of stakeholders (journalists, people, doctors, and politicians), in three groups of Italian regions (0,1,2), grouped according to the impact of the COVID-19 crises as defined by the Conte Government Ministerial Decree (8th March 2020). We then applied B-VAR techniques to analyze the sentiment relationships between the groups of stakeholders in every Region Groups. Results show a high influence of doctors at the beginning of the epidemic in the Group that includes most of Italian regions (Group 0), and in Lombardy that has been the region of Italy hit the most by the pandemic (Group 2). Our outcomes suggest that, given the role played by stakeholders and the COVID-19 magnitude, health policy interventions based on communication strategies may be used as best practices to develop regional mitigation plans for the containment and contrast of epidemiological emergencies.

Early warnings of COVID-19 outbreaks across Europe from social media.

We analyze data from Twitter to uncover early-warning signals of COVID-19 outbreaks in Europe in the winter season 2019-2020, before the first public announcements of local sources of infection were made. We show evidence that unexpected levels of concerns about cases of pneumonia were raised across a number of European countries. Whistleblowing came primarily from the geographical regions that eventually turned out to be the key breeding grounds for infections. These findings point to the urgency of setting up an integrated digital surveillance system in which social media can help geo-localize chains of contagion that would otherwise proliferate almost completely undetected.

The role of European health system characteristics in affecting Covid 19 lethality during the early days of the pandemic.

This article examines the main factors affecting COVID-19 lethality across 16 European Countries with a focus on the role of health system characteristics during the first phase of the diffusion of the virus. Specifically, we investigate the leading causes of lethality at 10, 20, 30, 40 days in the first hit of the pandemic. Using a random forest regression (ML), with lethality as outcome variable, we show that the percentage of people older than 65 years (with two or more chronic diseases) is the main predictor variable of lethality by COVID-19, followed by the number of hospital intensive care unit beds, investments in healthcare spending compared to GDP, number of nurses and doctors. Moreover, the variable of general practitioners has little but significant predicting quality. These findings contribute to provide evidence for the prediction of lethality caused by COVID-19 in Europe and open the discussion on health policy and management of health care and ICU beds during a severe epidemic.

A social network analysis of the organizations focusing on tuberculosis, malaria and pneumonia.

In this paper,we present an original study on the use of social media data to analyze the structure of the global health networks (GHNs) relative to health organizations targeted to malaria, tuberculosis (TBC) and pneumonia as well as twitter popularity, evaluating the performance of their strategies in response to the arising health threats. We use a machine learning ensemble classifier and social network analysis to discover the Twitter users that represent organizations or groups active for each disease. We have found evidence that the GHN of TBC is the more mature, active and global. Meanwhile, the networks of malaria and pneumonia are found to be less connected and lacking global coverage. Our analysis validates the use of social media to analyze GHNs and to propose these networks as an important organizational tool in mobilizing the community versus global sustainable development goals.

High-skilled labour mobility in Europe before and after the 2004 enlargement.

The extent to which international high-skilled mobility channels are forming is a question of great importance in an increasingly global knowledge-based economy. One factor facilitating the growth of high-skilled labour markets is the standardization of certifiable degrees meriting international recognition. Within this context, we analysed an extensive high-skilled mobility database comprising roughly 382 000 individuals from five broad profession groups (Medical, Education, Technical, Science & Engineering and Business & Legal) over the period 1997-2014, using the 13-country expansion of the European Union (EU) to provide insight into labour market integration. We compare the periods before and after the 2004 enlargement, showing the emergence of a new east-west migration channel between the 13 mostly eastern EU entrants (E) and the rest of the western European countries (W). Indeed, we observe a net directional loss of human capital from E → W, representing 29% of the total mobility after 2004. Nevertheless, the counter-migration from W → E is 7% of the total mobility over the same period, signalling the emergence of brain circulation within the EU. Our analysis of the country-country mobility networks and the country-profession bipartite networks provides timely quantitative evidence for the convergent integration of the EU, and highlights the central role of the UK and Germany as high-skilled labour hubs. We conclude with two data-driven models to explore the structural dynamics of the mobility networks. First, we develop a reconfiguration model to explore the potential ramifications of Brexit and the degree to which redirection of high-skilled labourers away from the UK may impact the integration of the rest of the European mobility network. Second, we use a panel regression model to explain empirical high-skilled mobility rates in terms of various economic 'push-pull' factors, the results of which show that government expenditure on education, per capita wealth, geographical proximity and labour force size are significant attractive features of destination countries.

The Accounting Network: How Financial Institutions React to Systemic Crisis.

The role of Network Theory in the study of the financial crisis has been widely spotted in the latest years. It has been shown how the network topology and the dynamics running on top of it can trigger the outbreak of large systemic crisis. Following this methodological perspective we introduce here the Accounting Network, i.e. the network we can extract through vector similarities techniques from companies' financial statements. We build the Accounting Network on a large database of worldwide banks in the period 2001-2013, covering the onset of the global financial crisis of mid-2007. After a careful data cleaning, we apply a quality check in the construction of the network, introducing a parameter (the Quality Ratio) capable of trading off the size of the sample (coverage) and the representativeness of the financial statements (accuracy). We compute several basic network statistics and check, with the Louvain community detection algorithm, for emerging communities of banks. Remarkably enough sensible regional aggregations show up with the Japanese and the US clusters dominating the community structure, although the presence of a geographically mixed community points to a gradual convergence of banks into similar supranational practices. Finally, a Principal Component Analysis procedure reveals the main economic components that influence communities' heterogeneity. Even using the most basic vector similarity hypotheses on the composition of the financial statements, the signature of the financial crisis clearly arises across the years around 2008. We finally discuss how the Accounting Networks can be improved to reflect the best practices in the financial statement analysis.

Users Polarization on Facebook and Youtube.

Users online tend to select information that support and adhere their beliefs, and to form polarized groups sharing the same view-e.g. echo chambers. Algorithms for content promotion may favour this phenomenon, by accounting for users preferences and thus limiting the exposure to unsolicited contents. To shade light on this question, we perform a comparative study on how same contents (videos) are consumed on different online social media-i.e. Facebook and YouTube-over a sample of 12M of users. Our findings show that content drives the emergence of echo chambers on both platforms. Moreover, we show that the users' commenting patterns are accurate predictors for the formation of echo-chambers.

Global value trees.

The fragmentation of production across countries has become an important feature of the globalization in recent decades and is often conceptualized by the term "global value chains" (GVCs). When empirically investigating the GVCs, previous studies are mainly interested in knowing how global the GVCs are rather than how the GVCs look like. From a complex networks perspective, we use the World Input-Output Database (WIOD) to study the evolution of the global production system. We find that the industry-level GVCs are indeed not chain-like but are better characterized by the tree topology. Hence, we compute the global value trees (GVTs) for all the industries available in the WIOD. Moreover, we compute an industry importance measure based on the GVTs and compare it with other network centrality measures. Finally, we discuss some future applications of the GVTs.

Twitter-Based Analysis of the Dynamics of Collective Attention to Political Parties.

Large-scale data from social media have a significant potential to describe complex phenomena in the real world and to anticipate collective behaviors such as information spreading and social trends. One specific case of study is represented by the collective attention to the action of political parties. Not surprisingly, researchers and stakeholders tried to correlate parties' presence on social media with their performances in elections. Despite the many efforts, results are still inconclusive since this kind of data is often very noisy and significant signals could be covered by (largely unknown) statistical fluctuations. In this paper we consider the number of tweets (tweet volume) of a party as a proxy of collective attention to the party, identify the dynamics of the volume, and show that this quantity has some information on the election outcome. We find that the distribution of the tweet volume for each party follows a log-normal distribution with a positive autocorrelation of the volume over short terms, which indicates the volume has large fluctuations of the log-normal distribution yet with a short-term tendency. Furthermore, by measuring the ratio of two consecutive daily tweet volumes, we find that the evolution of the daily volume of a party can be described by means of a geometric Brownian motion (i.e., the logarithm of the volume moves randomly with a trend). Finally, we determine the optimal period of averaging tweet volume for reducing fluctuations and extracting short-term tendencies. We conclude that the tweet volume is a good indicator of parties' success in the elections when considered over an optimal time window. Our study identifies the statistical nature of collective attention to political issues and sheds light on how to model the dynamics of collective attention in social media.

Credit Default Swaps networks and systemic risk.

Credit Default Swaps (CDS) spreads should reflect default risk of the underlying corporate debt. Actually, it has been recognized that CDS spread time series did not anticipate but only followed the increasing risk of default before the financial crisis. In principle, the network of correlations among CDS spread time series could at least display some form of structural change to be used as an early warning of systemic risk. Here we study a set of 176 CDS time series of financial institutions from 2002 to 2011. Networks are constructed in various ways, some of which display structural change at the onset of the credit crisis of 2008, but never before. By taking these networks as a proxy of interdependencies among financial institutions, we run stress-test based on Group DebtRank. Systemic risk before 2008 increases only when incorporating a macroeconomic indicator reflecting the potential losses of financial assets associated with house prices in the US. This approach indicates a promising way to detect systemic instabilities.

Voting behavior, coalitions and government strength through a complex network analysis.

We analyze the network of relations between parliament members according to their voting behavior. In particular, we examine the emergent community structure with respect to political coalitions and government alliances. We rely on tools developed in the Complex Network literature to explore the core of these communities and use their topological features to develop new metrics for party polarization, internal coalition cohesiveness and government strength. As a case study, we focus on the Chamber of Deputies of the Italian Parliament, for which we are able to characterize the heterogeneity of the ruling coalition as well as parties specific contributions to the stability of the government over time. We find sharp contrast in the political debate which surprisingly does not imply a relevant structure based on established parties. We take a closer look to changes in the community structure after parties split up and their effect on the position of single deputies within communities. Finally, we introduce a way to track the stability of the government coalition over time that is able to discern the contribution of each member along with the impact of its possible defection. While our case study relies on the Italian parliament, whose relevance has come into the international spotlight in the present economic downturn, the methods developed here are entirely general and can therefore be applied to a multitude of other scenarios.

A multi-level geographical study of Italian political elections from Twitter data.

In this paper we present an analysis of the behavior of Italian Twitter users during national political elections. We monitor the volumes of the tweets related to the leaders of the various political parties and we compare them to the elections results. Furthermore, we study the topics that are associated with the co-occurrence of two politicians in the same tweet. We cannot conclude, from a simple statistical analysis of tweet volume and their time evolution, that it is possible to precisely predict the election outcome (or at least not in our case of study that was characterized by a "too-close-to-call" scenario). On the other hand, we found that the volume of tweets and their change in time provide a very good proxy of the final results. We present this analysis both at a national level and at smaller levels, ranging from the regions composing the country to macro-areas (North, Center, South).

Extraction of temporal networks from term co-occurrences in online textual sources.

A stream of unstructured news can be a valuable source of hidden relations between different entities, such as financial institutions, countries, or persons. We present an approach to continuously collect online news, recognize relevant entities in them, and extract time-varying networks. The nodes of the network are the entities, and the links are their co-occurrences. We present a method to estimate the significance of co-occurrences, and a benchmark model against which their robustness is evaluated. The approach is applied to a large set of financial news, collected over a period of two years. The entities we consider are 50 countries which issue sovereign bonds, and which are insured by Credit Default Swaps (CDS) in turn. We compare the country co-occurrence networks to the CDS networks constructed from the correlations between the CDS. The results show relatively small, but significant overlap between the networks extracted from the news and those from the CDS correlations.

DebtRank: too central to fail? Financial networks, the FED and systemic risk.

Systemic risk, here meant as the risk of default of a large portion of the financial system, depends on the network of financial exposures among institutions. However, there is no widely accepted methodology to determine the systemically important nodes in a network. To fill this gap, we introduce, DebtRank, a novel measure of systemic impact inspired by feedback-centrality. As an application, we analyse a new and unique dataset on the USD 1.2 trillion FED emergency loans program to global financial institutions during 2008-2010. We find that a group of 22 institutions, which received most of the funds, form a strongly connected graph where each of the nodes becomes systemically important at the peak of the crisis. Moreover, a systemic default could have been triggered even by small dispersed shocks. The results suggest that the debate on too-big-to-fail institutions should include the even more serious issue of too-central-to-fail.