Socioeconomic Patterns of Twitter User Activity.

Stratifying behaviors based on demographics and socioeconomic status is crucial for political and economic planning. Traditional methods to gather income and demographic information, like national censuses, require costly large-scale surveys both in terms of the financial and the organizational resources needed for their successful collection. In this study, we use data from social media to expose how behavioral patterns in different socioeconomic groups can be used to infer an individual's income. In particular, we look at the way people explore cities and use topics of conversation online as a means of inferring individual socioeconomic status. Privacy is preserved by using anonymized data, and abstracting human mobility and online conversation topics as aggregated high-dimensional vectors. We show that mobility and hashtag activity are good predictors of income and that the highest and lowest socioeconomic quantiles have the most differentiated behavior across groups.

Geographical fragmentation of the global network of Twitter communications.

Understanding the geography of society represents a challenge for social and economic sciences. The recent availability of data from social media enables the observation of societies at a global scale. In this paper, we study the geographical structure of the Twitter communication network at the global scale. We find a complex structure where self-organized patches with clear cultural, historical, and administrative boundaries are manifested and first-world economies centralize information flows. These patches unveil world regions that are socially closer to each other with direct implications for processes of collective learning and identity creation.

Scale, context, and heterogeneity: the complexity of the social space.

The social space refers to physical or virtual places where people interact with one another. It decisively influences the emergence of human behaviors. However, little is known about the nature and complexity of the social space, nor its relationship to context and spatial scale. Recently, the science of complex systems has bridged between fields of knowledge to provide quantitative responses to fundamental sociological questions. In this paper, we analyze the shifting behavior of social space in terms of human interactions and wealth distribution across multiple scales using fine-grained data collected from both official (US Census Bureau) and unofficial data sources (social media). We use these data to unveil how patterns strongly depend upon the observation scale. Therefore, it is crucial for any analysis to be framed within the appropriate context to avoid biased results and/or misleading conclusions. Biased data analysis may lead to the adoption of fragile and poor decisions. Including context and a proper understanding of the spatial scale are essential nowadays, especially with the pervasive role of data-driven tools in decision-making processes.

Segregation dynamics with reinforcement learning and agent based modeling.

Societies are complex. Properties of social systems can be explained by the interplay and weaving of individual actions. Rewards are key to understand people's choices and decisions. For instance, individual preferences of where to live may lead to the emergence of social segregation. In this paper, we combine Reinforcement Learning (RL) with Agent Based Modeling (ABM) in order to address the self-organizing dynamics of social segregation and explore the space of possibilities that emerge from considering different types of rewards. Our model promotes the creation of interdependencies and interactions among multiple agents of two different kinds that segregate from each other. For this purpose, agents use Deep Q-Networks to make decisions inspired on the rules of the Schelling Segregation model and rewards for interactions. Despite the segregation reward, our experiments show that spatial integration can be achieved by establishing interdependencies among agents of different kinds. They also reveal that segregated areas are more probable to host older people than diverse areas, which attract younger ones. Through this work, we show that the combination of RL and ABM can create an artificial environment for policy makers to observe potential and existing behaviors associated to rules of interactions and rewards.

US social fragmentation at multiple scales.

Despite global connectivity, societies seem to be increasingly polarized and fragmented. This phenomenon is rooted in the underlying complex structure and dynamics of social systems. Far from homogeneously mixing or adopting conforming views, individuals self-organize into groups at multiple scales, ranging from families up to cities and cultures. In this paper, we study the fragmented structure of American society using mobility and communication networks obtained from geo-located social media data. We find self-organized patches with clear geographical borders that are consistent between physical and virtual spaces. The patches have multi-scale structure ranging from parts of a city up to the entire nation. Their significance is reflected in distinct patterns of collective interests and conversations. Finally, we explain the patch emergence by a model of network growth that combines mechanisms of geographical distance gravity, preferential attachment and spatial growth. Our observations are consistent with the emergence of social groups whose separated association and communication reinforce distinct identities. Rather than eliminating borders, the virtual space reproduces them as people mirror their offline lives online. Understanding the mechanisms driving the emergence of fragmentation in hyper-connected social systems is imperative in the age of the Internet and globalization.

Segregation and polarization in urban areas.

Social behaviours emerge from the exchange of information among individuals-constrained by and reciprocally influencing the structure of information flows. The Internet radically transformed communication by democratizing broadcast capabilities and enabling easy and borderless formation of new acquaintances. However, actual information flows are heterogeneous and confined to self-organized echo-chambers. Of central importance to the future of society is understanding how existing physical segregation affects online social fragmentation. Here, we show that the virtual space is a reflection of the geographical space where physical interactions and proximity-based social learning are the main transmitters of ideas. We show that online interactions are segregated by income just as physical interactions are, and that physical separation reflects polarized behaviours beyond culture or politics. Our analysis is consistent with theoretical concepts suggesting polarization is associated with social exposure that reinforces within-group homogenization and between-group differentiation, and they together promote social fragmentation in mirrored physical and virtual spaces.

Identifying seasonal mobility profiles from anonymized and aggregated mobile phone data. Application in food security.

We propose a framework for the systematic analysis of mobile phone data to identify relevant mobility profiles in a population. The proposed framework allows finding distinct human mobility profiles based on the digital trace of mobile phone users characterized by a Matrix of Individual Trajectories (IT-Matrix). This matrix gathers a consistent and regularized description of individual trajectories that enables multi-scale representations along time and space, which can be used to extract aggregated indicators such as a dynamic multi-scale population count. Unsupervised clustering of individual trajectories generates mobility profiles (clusters of similar individual trajectories) which characterize relevant group behaviors preserving optimal aggregation levels for detailed and privacy-secured mobility characterization. The application of the proposed framework is illustrated by analyzing fully anonymized data on human mobility from mobile phones in Senegal at the arrondissement level over a calendar year. The analysis of monthly mobility patterns at the livelihood zone resolution resulted in the discovery and characterization of seasonal mobility profiles related with economic activities, agricultural calendars and rainfalls. The use of these mobility profiles could support the timely identification of mobility changes in vulnerable populations in response to external shocks (such as natural disasters, civil conflicts or sudden increases of food prices) to monitor food security.

Global patterns of synchronization in human communications.

Social media are transforming global communication and coordination and provide unprecedented opportunities for studying socio-technical domains. Here we study global dynamical patterns of communication on Twitter across many scales. Underlying the observed patterns is both the diurnal rotation of the Earth, day and night, and the synchrony required for contingency of actions between individuals. We find that urban areas show a cyclic contraction and expansion that resembles heartbeats linked to social rather than natural cycles. Different urban areas have characteristic signatures of daily collective activities. We show that the differences detected are consistent with a new emergent global synchrony that couples behaviour in distant regions across the world. Although local synchrony is the major force that shapes the collective behaviour in cities, a larger-scale synchronization is beginning to occur.