EMOTIONAL TEXT MINING OF SOCIAL NETWORKS: THE FRENCH PRE-ELECTORAL SENTIMENT ON MIGRATION
Abstract
Migration has actually gained considerable relevance both in the national and European political agendas and in general public debate. It is a challenge for governments, which needs coordinated responses to ensure citizens’ security. Furthermore, the terrorist attacks against western countries have called into question freedom of movement and residence for people within the European Union. In the electoral campaign, the populist rhetoric on migration has largely exploited citizens’ perception of insecurity, as in the French presidential electoral campaign of 2017. In order to analyse public sentiment on migration, we collected with twittweR of R Statistics a sample of 111767 messages containing the word “migrant” produced in the last two weeks before the first-round votes from the Twitter repository. The messages were collected in a large size corpus of over two million tokens to which we applied multivariate techniques, i.e. cluster analysis with a bisecting k- means algorithm and a correspondence analysis on the keyword per cluster matrix, in order to identify the contents and the sentiments behind the shared comments. The results show how the clusters and the factorial space are representative of the different ways of emotionally representing migration, highlighting the relevant aspects perceived by those who choose to express themselves through Twitter.
IMPATTI DELL’AUTOMAZIONE SUL MERCATO DEL LAVORO. PRIME STIME PER IL CASO ITALIANO
Abstract
The causes of the present decline of demand in labor markets in developed countries are subject to considerable theoretical debate. More specifically, according to some authors, globalization and offshoring together with technological innovation, could lead to further negative impacts on real employment.
Some studies estimate that the contribution of automation is the actual cause of job loss: in the US the introduction of robots by 2021 could lead to a cut of more than 6% of the workforce (FORRESTER 2016), and as much as 54% in Europe in the coming decades (Bowles 2014), although the greatest impact would occur in developing countries, where automation could weaken the traditional comparative advantages in terms of labor costs (UN 2016).
The Italian case is particularly interesting, as the automation was introduced in large enterprises over three decades ago, determining a deep impact in terms of loss for low skilled jobs.
This paper aims to provide a first quantification of the impacts on Italian labor market determined by the spread of latest technological innovations, both in terms of employment levels and social/territorial mobility, by differentiating its effects per macro-geographical breakdown of the country
“THE GRIEF THAT DOESN’T SPEAK”: TEXT MINING AND BRAIN STRUCTURE
F. Greco, D. Laricchiuta, F. Piras, B. Cordella, D. Cutuli, E. Picerni, F. Assogna, C. Lai, G. Spalletta, L. Petrosini10
Abstract
Contemporary neurosciences have shown that emotions, thought and language involve the functioning of connected brain areas, which allow the recognition and expression of one’s own feelings.
The scope of this pilot study is to investigate the link among the verbal expression of emotional experiences (assessed with the Toronto Structured Interview for Alexithymia – TSIA -), the linguistic structure and the brain structure.
To this aim, 9 healthy adult subjects of both sexes were interviewed by means of the TSIA and the cortical and subcortical structural measures were detected. The TSIA transcripts were analysed by using a cluster analysis and, subsequently, a correspondence analysis, and the values of factors were correlated with cortical and subcortical structural measures as well as TSIA scores, evidencing significant associations.
The study highlighted that in healthy subjects it is possible to identify a link between the manner in which people express their experiences, recognize and use their emotions and the brain structural correlates.
DOMINIO: A MODULAR AND SCALABLE TOOL FOR THE OPEN SOURCE INTELLIGENCE
Abstract
Prisma has developed an innovative technology for the Open Source Intelligence (OSINT) which aims to provide a solution for those processes of knowledge management, which require the intervention of a human operator, unaided by information technology (IT) support, in one or more stages of the procedure.
Such intervention involves a considerable waste of time and resources that could be reduced through the use of an IT tool, partially or totally automating entire stages of the procedure. DOMINIO is a platform that implements tools for automatic online information aggregation, its analysis, the possible alignment with traditional databases and the representation through infographic and georeferencing tools, in order to generate a report. This paper describes the platform architecture, the main algorithms used in the analysis stage of the contents and possible directions of development.