The effects of online social media on critical issues, such as polarization and misinformation, are under scrutiny due to the disruptive consequences that these phenomena can have on our societies. Among the algorithms routinely used by social media platforms, people-recommender systems are of special interest, as they directly contribute to the evolution of the social network structure, affecting the information and the opinions users are exposed to. In this paper, we propose a novel framework to assess the effect of people recommenders on the evolution of opinions. Our proposal is based on Monte Carlo simulations combining link recommendation and opinion-dynamics models. In order to control initial conditions, we define a random network model to generate graphs with opinions, with tunable amounts of modularity and homophily. Finally, we join these elements into a methodology able to study the causal relationship between the recommender system and the echo chamber effect. Our method can also assess if such relationships are statistically significant. We also show how such a framework can be used to measure, by means of simulations, the impact of different intervention strategies. Our thorough experimentation shows that people recommenders can in fact lead to a significant increase in echo chambers. However, this happens only if there is considerable initial homophily in the network. Also, we find that if the network already contains echo chambers, the effect of the recommendation algorithm is negligible. Such findings are robust to two very different opinion dynamics models, a bounded confidence model and an epistemological model.

No abstract

Despite echo chambers in social media have been under considerable scrutiny, general models for their detection and analysis are missing. In this work, we aim to ll this gap by proposing a probabilistic generative model that explains social media footprints-i.e., social network structure and propagations of information-through a set of latent communities, characterized by a degree of echochamber behavior and by an opinion polarity. Speci cally, echo chambers are modeled as communities that are permeable to pieces of information with similar ideological polarity, and impermeable to information of opposed leaning: this allows discriminating echo chambers from communities that lack a clear ideological alignment.To learn the model parameters we propose a scalable, stochastic adaptation of the Generalized Expectation Maximization algorithm, that optimizes the joint likelihood of observing social connections and information propagation. Experiments on synthetic data show that our algorithm is able to correctly reconstruct ground-truth latent communities with their degree of echo-chamber behavior and opinion polarity. Experiments on real-world data about polarized social and political debates, such as the Brexit referendum or the COVID-19 vaccine campaign, con rm the e ectiveness of our proposal in detecting echo chambers. Finally, we show how our model can improve accuracy in auxiliary predictive tasks, such as stance detection and prediction of future propagations.

With a radical energy transition fostered by the increased deployment of renewable non-programmable energy sources over conventional ones, the forecasting of distributed energy production and consumption is becoming a cornerstone to ensure grid security and efficient operational planning. Due to the distributed and fragmented design of such systems, real-time observability of Distributed Generation operations beyond the Transmission System Operator domain is not always granted. In this context, we propose a Machine Learning pipeline for forecasting distributed energy production and consumption in an electrical grid at the HV distribution substation level, where data from distributed generation is partially observable. The proposed methodology is validated on real data for a large Italian region. Results show that the proposed model is able to predict up to 7 days ahead the amount of load and distributed generation (and the net power flux by difference) at each HV distribution substation with a 24%-44% mean gain in out-of-sample accuracy against a non-naive baseline model, paving the way to advanced and more efficient power system management.

We propose a model for the synthetic generation of information cascades in social media. In our model the information “memes” propagating in the social network are characterized by a probability distribution in a topic space, accompanied by a textual description, i.e., a bag of keywords coherent with the topic distribution. Similarly, every user of the social media is described by a vector of interests defined over the same topic space. Information cascades are governed by the topic of the meme, its level of virality, the interests of each user, community pressure, and social influence.The main technical challenge we face towards our goal is the generation of realistic interest vectors, given a known network structure and a tunable level of homophily. We tackle this problem by means of a method based on non-negative matrix factorization, which is shown experimentally to outperform non-trivial baselines based on label propagation and random-walk-based graph embedding.As we showcase in our experiments, our model offers a small set of simple and easily interpretable “knobs” which allow to study, in vitro, how each set of assumptions affects the resulting propagations. Finally, we show how to generate synthetic cascades that have similar macro-statistics to the real-world cascades for a dataset containing both the network and the cascades.