Using deep-learning algorithms to derive basic characteristics of social media users: The Brexit campaign as a case study.

A recurrent criticism concerning the use of online social media data in political science research is the lack of demographic information about social media users. By employing a face-recognition algorithm to the profile pictures of Facebook users, the paper derives two fundamental demographic characteristics (age and gender) of a sample of Facebook users who interacted with the most relevant British parties in the two weeks before the Brexit referendum of 23 June 2016. The article achieves the goals of (i) testing the precision of the algorithm, (ii) testing its validity, (iii) inferring new evidence on digital mobilisation, and (iv) tracing the path for future developments and application of the algorithm. The findings show that the algorithm is reliable and that it can be fruitfully used in political and social sciences both to confirm the validity of survey data and to obtain information from populations that are generally unavailable within traditional surveys.

The Spreading of Cohabitation as a Diffusion Process: Evidence from Italy.

Drawing on seminal work by Nazio and Blossfeld (Eur J Popul 19(1):47-82, 2003) and Di Giulio and Rosina (Demogr Res 16(14):441-468, 2007), this paper tests whether the recent spread of cohabitation in Italy has followed the typical pattern of diffusion of innovation processes. In doing so, we contribute to the debate on the determinants of the emergence of "new" family behaviour. Following previous literature, innovative behaviour should spread initially through direct social modelling, i.e. interpersonal communication among highly selected individuals (peer effects). At later stages, the diffusion should spread through knowledge awareness of the innovation, i.e. communication with previous generations (pre-cohort effects), so that also less selected individuals are prone to adopt the new behaviour. In the specific Italian context-a Catholic, "familistic" setting, with high normative pressure and importance of parental approval-we surmise the influence of previous generations to be dominant. We use data from the "Family and Social Subjects" survey carried out by Istat (2009) and apply Event History Analysis in the form of competing-risks exponential models to study Italian women's transition to cohabitation as first partnership. Results suggest that the most important driver of the spreading of cohabitation in Italy is represented by the degree of its diffusion among older cohorts. However, we find a positive and significant interaction between women's education and peer effects at the onset of the phenomenon, in line with the Second Demographic Transition (SDT) hypothesis. Cohabitation is also more likely if parents experienced separation/divorce and, more generally, if the environment of the family of origin can be described as "SDT-friendly".