Can large language model (LLM) agents reproduce the complex social dynamics that characterize human online behavior -- shaped by homophily, reciprocity, and social validation -- and what memory and learning mechanisms enable such dynamics to emerge? We present a multi-agent LLM simulation framework in which agents repeatedly interact, evaluate one another, and adapt their behavior through in-context learning accelerated by a coaching signal. To model human social behavior, we design behavioral reward functions that capture core drivers of online engagement, including social interaction, information seeking, self-presentation, coordination, and emotional support. These rewards align agent objectives with empirically observed user motivations, enabling the study of how network structures and group formations emerge from individual decision-making. Our experiments show that coached LLM agents develop stable interaction patterns and form emergent social ties, yielding network structures that mirror properties of real online communities. By combining behavioral rewards with in-context adaptation, our framework establishes a principled testbed for investigating collective dynamics in LLM populations and reveals how artificial agents may approximate or diverge from human-like social behavior.

In the quest of accurate vertex classification, we introduce GRAVITY (Graph-based Representation leArning via Vertices Interaction TopologY), a framework inspired by physical systems where objects self-organize under attractive forces. GRAVITY models each vertex as exerting influence through learned interactions shaped by structural proximity and attribute similarity. These interactions induce a latent potential field in which vertices move toward energy efficient positions, coalescing around class-consistent attractors and distancing themselves from unrelated groups. Unlike traditional message-passing schemes with static neighborhoods, GRAVITY adaptively modulates the receptive field of each vertex based on a learned force function, enabling dynamic aggregation driven by context. This field-driven organization sharpens class boundaries and promotes semantic coherence within latent clusters. Experiments on real-world benchmarks show that GRAVITY yields competitive embeddings, excelling in both transductive and inductive vertex classification tasks.

While Agent-Based Models can create detailed artificial societies based on individual differences and local context, they can be computationally intensive. Modelers may offset these costs through a parsimonious use of the model, for example by using smaller population sizes (which limits analyses in sub-populations), running fewer what-if scenarios, or accepting more uncertainty by performing fewer simulations. Alternatively, researchers may accelerate simulations via hardware solutions (e.g., GPU parallelism) or approximation approaches that operate a tradeoff between accuracy and compute time. In this paper, we present an approximation that combines agents who `think alike', thus reducing the population size and the compute time. Our innovation relies on representing agent behaviors as networks of rules (Fuzzy Cognitive Maps) and empirically evaluating different measures of distance between these networks. Then, we form groups of think-alike agents via community detection and simplify them to a representative agent. Case studies show that our simplifications remain accuracy.

Human interactions create social networks forming the backbone of societies. Individuals adjust their opinions by exchanging information through social interactions. Two recurrent questions are whether social structures promote opinion polarisation or consensus in societies and whether polarisation can be avoided, particularly on social media. In this paper, we hypothesise that not only network structure but also the timings of social interactions regulate the emergence of opinion clusters. We devise a temporal version of the Deffuant opinion model where pairwise interactions follow temporal patterns and show that burstiness alone is sufficient to refrain from consensus and polarisation by promoting the reinforcement of local opinions. Individuals self-organise into a multi-partisan society due to network clustering, but the diversity of opinion clusters further increases with burstiness, particularly when individuals have low tolerance and prefer to adjust to similar peers. The emergent opinion landscape is well-balanced regarding clusters' size, with a small fraction of individuals converging to extreme opinions. We thus argue that polarisation is more likely to emerge in social media than offline social networks because of the relatively low social clustering observed online. Counter-intuitively, strengthening online social networks by increasing social redundancy may be a venue to reduce polarisation and promote opinion diversity.

Have you ever watched a video or movie because YouTube or Netflix recommended it to you? Or added a friend on Facebook from the list of "people you may know"? And how does Twitter decide which tweets to show you at the top of your feed? These platforms are driven by algorithms, which rank and recommend content for us based on our data. If you want to know when social media companies are trying to manipulate you into disclosing information or engaging more, the answer is always.

Location plays an essential role in our lives, bridging our online and offline worlds. This paper explores the interplay of people's location, interactions, and social ties within a large real-world dataset. We present and evaluate Flap, a system that solves two intimately related tasks: link and location prediction in online social networks. For link prediction, Flap infers social ties by considering patterns in friendship formation, the content of people's messages, and user location. We show that while each component is a weak predictor of friendship alone, combining them results in a strong model---accurately identifying the majority of friendships. For location prediction, Flap implements a scalable probabilistic model of human mobility, where we treat users with known GPS positions as noisy sensors of the location of their friends. We explore supervised and unsupervised learning scenarios, and focus on the efficiency of both learning and inference. We evaluate Flap on a large sample of highly active users from two distinct geographical areas and show that it (1) reconstructs the entire friendship graph with high accuracy even when no edges are given; and (2) infers people's fine-grained location, even when they keep their data private and we can only access the location of their friends. Our models significantly outperform current approaches to either task.

Recent research suggests that, as in offline scenarios, spatial proximity increases the likelihood that two individuals establish an online social connection, and geographic closeness could therefore influence the formation of online communities. In this work we present a study of communities in two online social networks with location-sharing features and analyze their social and spatial properties. We study the places users visit to understand whether communities revolve around places or whether they exist independently. Our results suggest that community structure in social networks may arise from both social and spatial factors, so that exploiting information about the places where people go could benefit the definition of new community detection methods and community evolution models.

The popularity of the Web has allowed individuals to communicate and interact with each other on a global scale: people connect both to close friends and acquaintances, creating ties that can bridge otherwise separated groups of people. Recent evidence suggests that spatial distance is still affecting social links established on online platforms, with online ties preferentially connecting closer people. In this work we study the relationships between interaction strength, spatial distance and structural position of ties between members of a large-scale online social networking platform, Tuenti. We discover that ties in highly connected social groups tend to span shorter distances than connections bridging together otherwise separated portions of the network. We also find that such bridging connections have lower social interaction levels than ties within the inner core of the network and ties connecting to its periphery. Our results suggest that spatial constraints on online social networks are intimately connected to structural network properties, with important consequences for information diffusion.

Research in computational epidemiology to date has concentrated on coarse-grained statistical analysis of populations, often synthetic ones. By contrast, this paper focuses on fine-grained modeling of the spread of infectious diseases throughout a large real-world social network. Specifically, we study the roles that social ties and interactions between specific individuals play in the progress of a contagion. We focus on public Twitter data, where we find that for every health-related message there are more than 1,000 unrelated ones. This class imbalance makes classification particularly challenging. Nonetheless, we present a framework that accurately identifies sick individuals from the content of online communication. Evaluation on a sample of 2.5 million geo-tagged Twitter messages shows that social ties to infected, symptomatic people, as well as the intensity of recent co-location, sharply increase one's likelihood of contracting the illness in the near future. To our knowledge, this work is the first to model the interplay of social activity, human mobility, and the spread of infectious disease in a large real-world population. Furthermore, we provide the first quantifiable estimates of the characteristics of disease transmission on a large scale without active user participation---a step towards our ability to model and predict the emergence of global epidemics from day-to-day interpersonal interactions.

Location-based social networks (LBSNs) have become a popular form of social media in recent years. They provide location related services that allow users to "check-in'' at geographical locations and share such experiences with their friends. Millions of "check-in'' records in LBSNs contain rich information of social and geographical context and provide a unique opportunity for researchers to study user's social behavior from a spatial-temporal aspect, which in turn enables a variety of services including place advertisement, traffic forecasting, and disaster relief. In this paper, we propose a social-historical model to explore user's check-in behavior on LBSNs. Our model integrates the social and historical effects and assesses the role of social correlation in user's check-in behavior. In particular, our model captures the property of user's check-in history in forms of power-law distribution and short-term effect, and helps in explaining user's check-in behavior. The experimental results on a real world LBSN demonstrate that our approach properly models user's check-ins and shows how social and historical ties can help location prediction.