Mobile and Social Computing Lab


The main objective of MobS Lab is to build predictive and computational approaches to human behavior understanding using the newly ubiquitous sources of data that are becoming available about all aspects of human life (e.g. mobile phone data, credit card transactions, energy consumption data, social media data from Facebook, Twitter, Foursquare, etc.). Moreover, MobS aims also at using these computational models of human behaviors in order to design more efficient companies, cities and societies, and to solve challenges in several fields such as health, finance, crime, transportation, energy consumption and sustainability, unemployment, etc.

Contributions to Smart Cities and Communities

Nowadays, massive streams of human behavioral data and urban data combined with increased analytical capabilities are creating unprecedented possibilities for solving relevant problems for cities. The MobS Lab has leveraged mobile phone data, OpenStreetMap data, credit card transactions, Google Street View images in order (i) to infer how vital and livable a city is, (ii) to find the urban conditions (e.g. mixed land use, block sizes, employment and population densities, mobility routines, safety perception, etc.) that magnify and influence urban life, (iii) to study their relationship with societal outcomes such as poverty, criminality, innovation, segregation, environment sustainability, etc., and (iv) to envision data-driven guidelines for helping policy makers to respond to the demands of citizens. Currently, MobS Lab is co-leading a project on crime prediction in the six major cities of Colombia and contributing to the city sensing FBK flagship project.

Contributions to Data Science

MobS Lab is working in the emerging field of data-driven computational social science, at the intersection of several disciplines such as machine learning, social psychology, network science, complex systems, sociology, and urban science. Within the Data Science area, the unit will contribute to the research on data science for social good and the applications of data science approaches to social sciences, social psychology, economics, and urban science domains. MobS will be also involved in the new “laurea magistrale” in Data Science, launched by University of Trento and Fondazione Bruno Kessler.

Contributions to Artificial Intelligence

As agents that increasingly participate in, and affect, the lives of humans, computers need to explain and predict their human parties’ behavior by, e.g., deploying some kind of naïve folk-psychology in which the understanding of people’s personality can reasonably be expected to play a role. Thus, MobS has addressed some of the issues raised by the attempts at endowing machines with the capability of recognizing people’s personality in different settings such as social media usage, spending habits, daily routines, small group meetings, short self-presentations and job interviews, human-computer collaborative tasks, social scenarios where a group of people move freely and interact naturally, and so on. The unit also contributes to the emerging field of ethical and societal implications of Artificial Intelligence, with a focus on enhancing fairness, accountability and transparency in AI-driven decision-making processes.

Other research directions

MobS Lab is also working on innovative fintech/insurancetech solutions within the co-innovation lab with GFT. In particular, the unit is focused on devising innovative machine learning algorithms for customer profiling, credit scoring, and fraud detection. Another topic of interest is the design of decentralized (blockchain-based) data management and sharing solutions (this research direction is conducted in collaboration with the Security & Trust group).

Nowadays, we leave traces of our life events, behaviors, interests, and habits on social networks (e.g. Facebook statuses and tweets), using mobile phones and surfing the web. All this information together works as a powerful microscope that can help us to understand and predict health and well-being conditions of individuals. Detection of emotional states, happiness levels and depressive disorders, prediction of physical health conditions, and stress levels, and modeling of influenza spreading are some examples of the studies carried out in this area by MobS Lab.

Head of Unit