Carlo Piccardi

Paolo Tarantino, Fabio Mazza, Carlo Piccardi et al.

The ability of a small set of coordinated actors to manipulate opinions in online social networks poses a serious challenge to the fairness and integrity of public debate. We investigate this problem by studying how targeted stubborn agents can shift the average opinion of a network governed by the Hegselmann-Krause bounded-confidence dynamics. Experiments are conducted on weighted LFR benchmark networks with community structure, using multiple node-selection strategies based on degree, strength, PageRank, betweenness, k-coreness, s-coreness, and salience. We compare static interventions, in which stubborn agents keep a fixed extreme opinion, with dynamic interventions, in which their opinion gradually evolves from moderate to extreme values. Results show that dynamic strategies are substantially more effective than static ones, as they exploit bounded-confidence dynamics to progressively recruit intermediate agents and extend influence across the network. In contrast, static strategies tend to create early opinion separation and therefore have a more limited reach. We also find that while some centrality measures offer advantages in static settings, dynamic interventions can achieve strong performance even with simple or random node selection. Overall, the study clarifies how intervention design and target selection interact in shaping collective opinions, with implications for understanding and countering manipulation in social networks.

Francesco Pierri, Carlo Piccardi, Stefano Ceri

We tackle the problem of classifying news articles pertaining to disinformation vs mainstream news by solely inspecting their diffusion mechanisms on Twitter. Our technique is inherently simple compared to existing text-based approaches, as it allows to by-pass the multiple levels of complexity which are found in news content (e.g. grammar, syntax, style). We employ a multi-layer representation of Twitter diffusion networks, and we compute for each layer a set of global network features which quantify different aspects of the sharing process. Experimental results with two large-scale datasets, corresponding to diffusion cascades of news shared respectively in the United States and Italy, show that a simple Logistic Regression model is able to classify disinformation vs mainstream networks with high accuracy (AUROC up to 94%), also when considering the political bias of different sources in the classification task. We also highlight differences in the sharing patterns of the two news domains which appear to be country-independent. We believe that our network-based approach provides useful insights which pave the way to the future development of a system to detect misleading and harmful information spreading on social media.