Jacopo Nudo

The rise of digital platforms has enabled the large-scale observation of individual and collective behavior through high-resolution interaction data. This development has opened new analytical pathways for investigating how information circulates, how opinions evolve, and how coordination emerges in online environments. Yet despite a growing body of research, the field remains fragmented, marked by methodological heterogeneity, limited model validation, and weak integration across domains. In this survey, we address this gap by systematically reviewing the literature on online collective behavior, integrating empirical findings with formal modeling approaches. We examine platform-level regularities, the methodological choices used to identify them, and the extent to which existing modeling frameworks capture the observed dynamics. Rather than aiming for exhaustive coverage of individual subfields, we provide a structural and comparative synthesis of recurring empirical patterns, methodological approaches, and modeling assumptions that span across platforms and domains. The overarching goal is to consolidate a shared empirical baseline and to clarify the structural constraints shaping inference in this area, thereby laying the groundwork for more robust, comparable, and actionable analyses of online social media.

Large Language Models (LLMs) are increasingly embedded in evaluative processes, from information filtering to assessing and addressing knowledge gaps through explanation and credibility judgments. This raises the need to examine how such evaluations are built, what assumptions they rely on, and how their strategies diverge from those of humans. We benchmark six LLMs against expert ratings—NewsGuard and Media Bias/Fact Check—and against human judgments collected through a controlled experiment. We use news domains purely as a controlled benchmark for evaluative tasks, focusing on the underlying mechanisms rather than on news classification per se. To enable direct comparison, we implement a structured agentic framework in which both models and nonexpert participants follow the same evaluation procedure: selecting criteria, retrieving content, and producing justifications. Despite output alignment, our findings show consistent differences in the observable criteria guiding model evaluations, suggesting that lexical associations and statistical priors could influence evaluations in ways that differ from contextual reasoning. This reliance is associated with systematic effects: political asymmetries and a tendency to confuse linguistic form with epistemic reliability—a dynamic we term epistemia, the illusion of knowledge that emerges when surface plausibility replaces verification. Indeed, delegating judgment to such systems may affect the heuristics underlying evaluative processes, suggesting a shift from normative reasoning toward pattern-based approximation and raising open questions about the role of LLMs in evaluative processes.

The architecture of public discourse has been profoundly reshaped by social media platforms, which mediate interactions at an unprecedented scale and complexity. This study analyzes user behavior across six platforms over 33 years, exploring how the size of conversations and communities influences dialogue dynamics. Our findings reveal that smaller platforms foster richer, more sustained interactions, while larger platforms drive broader but shorter participation. Moreover, we observe that the propensity for users to reengage in a conversation decreases as community size grows, with niche environments as a notable exception, where participation remains robust. These findings show an interdependence between platform architecture, user engagement, and community dynamics, shedding light on how digital ecosystems shape the structure and quality of public discourse.

We investigate how Large Language Models (LLMs) behave when simulating political discourse on social media. Leveraging 21 million interactions on X during the 2024 U.S. presidential election, we construct LLM agents based on 1,186 real users, prompting them to reply to politically salient tweets under controlled conditions. Agents are initialized either with minimal ideological cues (Zero Shot) or recent tweet history (Few Shot), allowing one-to-one comparisons with human replies. We evaluate three model families (Gemini, Mistral, and DeepSeek) across linguistic style, ideological consistency, and toxicity. We find that richer contextualization improves internal consistency but also amplifies polarization, stylized signals, and harmful language. We observe an emergent distortion that we call "generation exaggeration": a systematic amplification of salient traits beyond empirical baselines. Our analysis shows that LLMs do not emulate users, they reconstruct them. Their outputs, indeed, reflect internal optimization dynamics more than observed behavior, introducing structural biases that compromise their reliability as social proxies. This challenges their use in content moderation, deliberative simulations, and policy modeling.

Language is a fundamental aspect of human societies, continuously evolving in response to various stimuli, including societal changes and intercultural interactions. Technological advancements have profoundly transformed communication, with social media emerging as a pivotal force that merges entertainment-driven content with complex social dynamics. As these platforms reshape public discourse, analyzing the linguistic features of user-generated content is essential to understanding their broader societal impact. In this paper, we examine the linguistic complexity of content produced by influential users on Twitter across three globally significant and contested topics: COVID-19, COP26, and the Russia-Ukraine war. By combining multiple measures of textual complexity, we assess how language use varies along four key dimensions: account type, political leaning, content reliability, and sentiment. Our analysis reveals significant differences across all four axes, including variations in language complexity between individuals and organizations, between profiles with sided versus moderate political views, and between those associated with higher versus lower reliability scores. Additionally, profiles producing more negative and offensive content tend to use more complex language, with users sharing similar political stances and reliability levels converging toward a common jargon. Our findings offer new insights into the sociolinguistic dynamics of digital platforms and contribute to a deeper understanding of how language reflects ideological and social structures in online spaces.