Essays on Bayesian Inference for Social Networks

This thesis presents Bayesian solutions to inference problems for three types of social network data structures: a single observation of a social network, repeated observations on the same social network, and repeated observations on a social network developing through time. A social network is conceived as being a structure consisting of actors and their social interaction with each other. A common conceptualisation of social networks is to let the actors be represented by nodes in a graph with edges between pairs of nodes that are relationally tied to each other according to some definition. Statistical analysis of social networks is to a large extent concerned with modelling of these relational ties, which lends itself to empirical evaluation. The first paper deals with a family of statistical models for social networks called exponential random graphs that takes various structural features of the network into account. In general, the likelihood functions of exponential random graphs are only known up to a constant of proportionality. A procedure for performing Bayesian inference using Markov chain Monte Carlo (MCMC) methods is presented. The algorithm consists of two basic steps, one in which an ordinary Metropolis-Hastings up-dating step is used, and another in which an importance sampling scheme is used to calculate the acceptance probability of the Metropolis-Hastings step. In paper number two a method for modelling reports given by actors (or other informants) on their social interaction with others is investigated in a Bayesian framework. The model contains two basic ingredients: the unknown network structure and functions that link this unknown network structure to the reports given by the actors. These functions take the form of probit link functions. An intrinsic problem is that the model is not identified, meaning that there are combinations of values on the unknown structure and the parameters in the probit link functions that are observationally equivalent. Instead of using restrictions for achieving identification, it is proposed that the different observationally equivalent combinations of parameters and unknown structure be investigated a posteriori. Estimation of parameters is carried out using Gibbs sampling with a switching devise that enables transitions between posterior modal regions. The main goal of the procedures is to provide tools for comparisons of different model specifications. Papers 3 and 4, propose Bayesian methods for longitudinal social networks. The premise of the models investigated is that overall change in social networks occurs as a consequence of sequences of incremental changes. Models for the evolution of social networks using continuos-time Markov chains are meant to capture these dynamics. Paper 3 presents an MCMC algorithm for exploring the posteriors of parameters for such Markov chains. More specifically, the unobserved evolution of the network in-between observations is explicitly modelled thereby avoiding the need to deal with explicit formulas for the transition probabilities. This enables likelihood based parameter inference in a wider class of network evolution models than has been available before. Paper 4 builds on the proposed inference procedure of Paper 3 and demonstrates how to perform model selection for a class of network evolution models.

Audiovisivi e Social Networks: il testo e i modi dell'esperienza 2007-2010

The doctoral research project "Audiovisuals and Social Networks: Text and Experiences 2007-2010" is mainly based on the analysis of the international audiovisuals landscape and of the promotional strategies of these products in Social Networks environment. The aim is to understand what kind of changes we can find about the concept of "text", users and marketing. The thesis is focused not just on Social Network marketing but also on new media development, such as Social TV and mobile.

Reti socievoli: l’impatto dei social networks nella costruzione dello spazio pubblico

La tesi si è consolidata nell’analisi dell’impatto dei social networks nella costruzione dello spazio pubblico, nella sfera di osservazione che è la rete e il web2.0. Osservando che il paradigma della società civile si sia modificato. Ridefinendo immagini e immaginari e forme di autorappresentazione sui new media (Castells, 2010). Nel presupposto che lo spazio pubblico “non è mai una realtà precostituita” (Innerarity, 2008) ma si muove all’interno di reti che generano e garantiscono socievolezza. Nell’obiettivo di capire cosa è spazio pubblico. Civic engagement che si rafforza in spazi simbolici (Sassen, 2008), nodi d’incontro significativi. Ivi cittadini-consumatori avanzano corresponsabilmente le proprie istanze per la debacle nei governi.. Cultura partecipativa che prende mossa da un nuovo senso civico mediato che si esprime nelle “virtù” del consumo critico. Portando la politica sul mercato. Cultura civica autoattualizzata alla ricerca di soluzioni alle crisi degli ultimi anni. Potere di una comunicazione che riduce il mondo ad un “villaggio globale” e mettono in relazione i pubblici connessi in spazi e tempi differenti, dando origine ad azioni collettive come nel caso degli Indignados, di Occupy Wall Street o di Rai per una notte. Emerge un (ri)pensare la citizenship secondo due paradigmi (Bennett,2008): l’uno orientato al governo attraverso i partiti, modello “Dutiful Citizenship”; l’altro, modello “Self Actualizing Citizenship” per cui i pubblici attivi seguono news ed eventi, percepiscono un minor obbligo nel governo, il voto è meno significativo per (s)fiducia nei media e nei politici. Mercato e società civile si muovono per il bene comune e una nuova “felicità”. La partecipazione si costituisce in consumerismo politico all’interno di reti in cui si sviluppano azioni individuali attraverso il social networking e scelte di consumo responsabile. Partendo dall’etnografia digitale, si è definito il modello “4 C”: Conoscenza > Coadesione > Co-partecipazione > Corresposabilità (azioni collettive) > Cultura-bility.

Networking: the "making of" social networks. A closer look at the process and antecedents of some resourcing-oriented behaviors in organizations.

Social networks are one of the “hot” themes in people’s life and contemporary social research. Considering our “embeddedness” in a thick web of social relations is a study perspective that could unveil a number of explanations of how people may manage their personal and social resources. Looking at people’s behaviors of building and managing their social networks, seems to be an effective way to find some possible rationalization about how to help people getting the best from their resources . The main aim of this dissertation is to give a closer look at the role of networking behaviors. Antecedents, motivations, different steps and measures about networking behaviors and outcomes are analyzed and discussed. Results seem to confirm, in a different setting and time perspective, that networking behaviors include different types and goals that change over time. Effects of networking behaviors seem to find empirical confirmation through social network analysis methods. Both personality and situational self-efficacy seem to predict networking behaviors. Different types of motivational drivers seem to be related to diverse networking behaviors.

Hypergraph Mining for Social Networks

Nowadays, more and more data is collected in large amounts, such that the need of studying it both efficiently and profitably is arising; we want to acheive new and significant informations that weren't known before the analysis. At this time many graph mining algorithms have been developed, but an algebra that could systematically define how to generalize such operations is missing. In order to propel the development of a such automatic analysis of an algebra, We propose for the first time (to the best of my knowledge) some primitive operators that may be the prelude to the systematical definition of a hypergraph algebra in this regard.

Analisi del comportamento e dello stato d'animo di pazienti malati del Morbo di Crohn tramite social networks

Al giorno d'oggi una pratica molto comune è quella di eseguire ricerche su Google per cercare qualsiasi tipo di informazione e molte persone, con problemi di salute, cercano su Google sintomi, consigli medici e possibili rimedi. Questo fatto vale sia per pazienti sporadici che per pazienti cronici: il primo gruppo spesso fa ricerche per rassicurarsi e per cercare informazioni riguardanti i sintomi ed i tempi di guarigione, il secondo gruppo invece cerca nuovi trattamenti e soluzioni. Anche i social networks sono diventati posti di comunicazione medica, dove i pazienti condividono le loro esperienze, ascoltano quelle di altri e si scambiano consigli. Tutte queste ricerche, questo fare domande e scrivere post o altro ha contribuito alla crescita di grandissimi database distribuiti online di informazioni, conosciuti come BigData, che sono molto utili ma anche molto complessi e che necessitano quindi di algoritmi specifici per estrarre e comprendere le variabili di interesse. Per analizzare questo gruppo interessante di pazienti gli sforzi sono stati concentrati in particolare sui pazienti affetti dal morbo di Crohn, che è un tipo di malattia infiammatoria intestinale (IBD) che può colpire qualsiasi parte del tratto gastrointestinale, dalla bocca all'ano, provocando una grande varietà di sintomi. E' stato fatto riferimento a competenze mediche ed informatiche per identificare e studiare ciò che i pazienti con questa malattia provano e scrivono sui social, al fine di comprendere come la loro malattia evolve nel tempo e qual'è il loro umore a riguardo.

Trust and Social Networks in a Changing Europe.

This project set out to investigate the effects of the recent massive social transitions in Eastern Europe on the everyday social lives of the inhabitants of three very different nations: Georgia, Russia and Hungary. It focused in particular on the availability and nature of the support networks available to three different segments of each of the societies (manual workers, students and entrepreneurs) and the impact of network participation on psychological and physical well-being. The group set four specific questions to investigate: the part played by individual psychological beliefs in the formation and maintenance of social networks and the consequent formation of trusting relations; the implication of the size and quality of these networks for mental health; the nature of the social groups inhabited by the respondents and the implication of their work schedule and daily routines on the maintenance of a social and family life; and an analysis of how cultures vary in their social networks and intimacy. Three different methods were used to examine social support and its implications: structured questionnaires, semi-structured short interviews and a media analysis of newspaper materials. The questionnaires were administered to 150 participants in each country, equally divided between students studying full time, manual workers employed in factories, and business people (small kiosk owners, whose work and life style differs considerably from that of the manual workers). The questionnaires investigated various predictors of social support including the locus of control, relationship beliefs, individualism-collectivism and egalitarianism, demographic variables (age, gender and occupation), social support, both in general and in relation to significant events that have occurred since the transition from communism. Those with an internal locus of control were more likely to report a higher level of social support, as were collectivists, while age too was a significant predictor, with younger respondents enjoying higher levels of support, regardless of the measures of support employed. Respondents across the cultures referred to a decline of social support and the group also found a direct correlation between social support and mental health outcomes. All 450 respondents were interviewed on their general responses to changes in their lives since the fall of communism and the effects of their work lives on their social lives and the home environment. The interviews revealed considerable variations in the way in which work-life offered opportunities for a broader social life and also provided a hindrance to the development of fulfilling relationships. Many of the work experiences discussed were culture specific, with work having a particularly negative impact on the social life of Russian entrepreneurs but being seen much more positively in Georgia. This may reflect the nature of support offered in a society as overall support levels were lowest in Russia, meaning that social support may be of particular importance there. The way in cultural values and norms about personal relationships are transmitted in a culture is a critical issue for social psychologists and the group examined newspaper articles in those newspapers read by the respondents in each of the three countries. These revealed a number of different themes. The concept of a divided society and its implications for personal relationships was clearest in Russian and Hungary, where widely-read newspapers dwelt on the contrast between "new Russians/Hungarians" and the older, poorer ones and extended considerable sympathy to those suffering from neglect in institutions. Magyar Nemzet, a paper widely read by Hungarian students reflects the generally more pessimistic tone about personal relationships in Russia and Hungary and gave a particularly detailed analysis of the implications this holds for human relations in a modern society. In Georgia, however, the tone of the newspapers is more positive, stressing greater social cohesion. Part of this cohesion is framed in the context of religion, with the church appealing to a broader egalitarianism, whereas in less egalitarian Hungary appeals by the Church are centred more on the nuclear family and its need for expansion in both size and influence. The division between the sexes was another prominent issue in Hungary and Russia, while the theme of generational conflict also emerged in Hungarian and Georgian papers, although with some understanding of "young people today". The team's original expectation that the different newspapers read by the different groups of respondents would present differing images of personal relationships was not fulfilled, as despite variations in style, they found little clear "ideological targeting" of any particular readership. They conclude that the vast majority of respondents recognised that the social transition from communism has had a significant impact on the well-being of social relationships and that this is a pertinent issue for all segments of society. While the group see the data collected as a source to be worked on for some time in the future, their initial impressions include the following. Social support is clearly an important concern across all three countries. All respondents (including the students) lament the time taken up by their heavy work schedules and value their social networks and family ties in particular. The level of social support differs across the countries investigated, with Georgian apparently enjoying significantly higher levels of social support. The analysis produced an image of a relatively cohesive and egalitarian society in which even the group most often seen as distant from the general population, business people, is supported by a strong social network. In contrast, the support networks available to the Russian respondents seem particularly weak and reflect a general sense of division and alienation within the culture as a whole. The implications of low levels of social support may vary across countries. While Russians reported the lowest level of mental health problems, the link between social support and mental health may be strongest in that country. In contrast, in Hungary it is the link between fatalism and mental health problems which is particularly strong, while in Georgia the strongest correlation was between mental health and marital quality, emphasising the significance of the marital relationship in that country.

Social Networks Analysis

This morning Dr. Risser will introduce you to the basic ideas of social network analysis. You will learn some history behind the study of social networks. Dr. Risser will introduce you to mathematical measures of social networks including centrality measures and measures of spread and cohesion. You will also learn how to use a computer program to analyze social network data

Social Networking: How to Build Social Networks

This poster illustrates variables and connections in social networking.