Searcharxiv⌕ Search

arXiv subjects

Chiara Boldrini

Publications and source records attributed to Chiara Boldrini.

At least 19 recordsLinked to original sources

Large Language Models as Digital Twins: a Distribution-Aware Questionnaire-Based Evaluation

This paper investigates whether Large Language Models can answer a personality questionnaire as a specific individual would. Given a user's social-media posts, the model completes the BFI-2-60 Big Five questionnaire as that user. The predicted responses are converted into trait scores and compared with the user's actual scores. We evaluate GPT-4, Gemma, Llama 3.1, and Mistral on the MyPersonality dataset. To determine whether predictions reflect information from the user's writing, we compare them with answers produced without user text and with values derived from general population tendencies. We measure prediction error across all users and separately for individuals with low, intermediate, and high trait scores. We also test whether an LLM can express an explicit personality profile when given only the target Big Five scores, without user text, and examine how predictions change as more text is provided. The results show that user text does not consistently improve performance. Models perform better near the middle of the trait distribution, while at the lower and upper ends they often remain close to central values or perform well at one end but poorly at the other. When given an explicit profile, GPT-4 most clearly translates trait information into consistent questionnaire responses, particularly for Extraversion and Neuroticism. Increasing context does not systematically reduce error: open-source models fluctuate more, whereas GPT-4 remains comparatively stable. Overall, the evaluated models do not consistently reproduce the questionnaire behavior of specific individuals.

cs.AI↗

The Cognitive Cost of LLM Writing: A Reading-Time Comparison with Human Text

Although linguistic differences between human-written and Large Language Model (LLM)-generated texts have been extensively studied, their implications for the cognitive effort involved in reading remain less explored. In psycholinguistics, reading time is commonly used as an indirect measure of cognitive processing effort. Building on this perspective, we investigate whether human-written texts and their LLM-generated rewrites exhibit differences in predicted reading time that may reflect differences in processing demands for readers. To this end, we introduce RoBERTa-RT, a model trained on human eye-tracking data to predict word-level reading times. We evaluate the model on both internal and external test sets, construct a paired dataset of 496 human-written articles and their LLM-generated rewrites, and apply RoBERTa-RT to compare their predicted reading times. Our findings show that LLM-generated rewrites tend to be shorter and have slightly lower predicted total reading times, while exhibiting higher predicted reading times per word. These differences are associated with systematic linguistic changes, including longer and less frequent words, greater lexical diversity, and higher contextual predictability. From a cognitive perspective, our findings suggest that LLM-generated writing may redistribute reading demands: reducing the amount of text to process while increasing the predicted processing effort associated with individual words. This highlights the importance of considering not only the linguistic characteristics of machine-generated content, but also its potential implications for human cognitive processing.

cs.CL↗

Rewiring the Majority: Structural Median Opinion Control in the Friedkin-Johnsen Model

Opinion control under the Friedkin-Johnsen (FJ) model has traditionally focused on modifying individual users, for example by changing their opinions or susceptibility to social influence. We study a complementary problem: can collective outcomes be steered by modifying the interaction network instead? We formulate structural median control as an edge-addition problem aimed at moving the equilibrium median beyond a target threshold. We show that the problem is NP-hard even under highly restricted settings and propose both continuous optimization methods and computationally lighter opinion-aware heuristics for selecting edge additions. Experiments on synthetic and real-world networks reveal that intervention success depends jointly on network topology, the placement of favorable opinions, and user susceptibility. Structural interventions produce the largest shifts when opinion placement and network structure allow added edges to create useful influence pathways toward the target outcome. Finally, under a homogeneous reference setting, we compare structural and node-level interventions using normalized budgets and a degree-weighted cost model. We show that, although node interventions often appear stronger under normalized budgets, structural interventions become competitive and frequently more cost-effective once the higher cost of targeting high-reach users is taken into account.

cs.SI↗

From Content Sharing to Opinion Shaping: A Theoretical Framework for Cascade-Driven Opinion Dynamics

Online social networks (OSNs) tightly couple information diffusion and opinion formation, yet most existing models treat these processes separately. Building on the Friedkin-Johnsen on Cascades (FJC) model, which integrates opinion updating within stochastic information cascades, we advance its analytical characterization and systematic validation. We derive an exact conditional layer-wise recursion that reveals the statistical coupling between diffusion realizations and opinion evolution, showing that a closed-form recursion in unconditional expectations is not available. To overcome this limitation, we introduce a mean-field decoupling approximation (MFA) that yields a tractable linear recursion for the expected opinion trajectory. We also develop scalable tree-based reductions that drastically reduce computational complexity while preserving structural diffusion properties, and validate the analytical recursion and its approximations through extensive simulations. Using Stochastic Block Model networks with controlled initial opinion configurations, we show that, unlike the classical Friedkin-Johnsen model, which typically leads to global homogenization, the FJC dynamics generate richer regimes of bounded assimilation and sustained polarization. Overall, this work bridges diffusion and influence modeling, providing a theoretical foundation for understanding how cascade-driven interactions reshape collective opinion landscapes in structured social networks.

cs.SI↗

Decentralised Federated Learning over Temporal Networks: The Role of Heterogeneities

Decentralised federated learning, based on peer-to-peer communication, is increasingly proposed for on-device training of machine learning models, promising a privacy-preserving, communication-efficient training process with no risk of single-point failure. However, the role of structural and temporal inhomogeneities in such fully decentralised settings remains poorly understood. Here, we investigate their effects when model parameters are locally averaged during aggregation. We show that the decentralised federated learning process is governed, both in the early phase and the late, stationary limit, by the same dynamics as a lazy random-walk diffusion process on temporal networks. Based on this mapping, we demonstrate that the typical experimental scenario used in decentralised federated learning leads to unrealistically rapid convergence because of ignoring the temporal and structural inhomogeneities inherent in the communication network. We analyse real-world temporal networks and find that inhomogeneities most often dramatically slow down diffusion, hence the convergence process.

cs.LG↗

Annotation of Positive vs Negative User Interactions for Social Sign Prediction

Inferring the sign of social relationships from online interactions is a fundamental challenge in social network analysis. Existing approaches typically rely on sentiment analysis to label individual interactions as positive or negative, then aggregate these labels to assign a sign to the relationship. However, sentiment analysis captures the valence of the content being discussed rather than the nature of the relational exchange itself, a conflation that can lead to systematic misclassification. In this paper, we propose a methodology that addresses this limitation by leveraging Large Language Models (LLMs) in a zero-shot setting to identify interaction-level relational signals (specifically, personal praise and personal attacks directed at the interlocutor) as more direct indicators of positive and negative social ties. We evaluate four models spanning open-weight and proprietary architectures (Qwen2.5:7b, Gemma2:9b, GPT-4o, GPT-5.4-mini) across three prompt designs of increasing complexity, on two human-annotated datasets of approximately 298 and 340 texts respectively. Results show that zero-shot LLMs achieve good classification performance on both tasks without any task-specific training data, establishing a practical baseline for relational annotation. Performance differs across tasks: attack detection is robust to prompt design and model choice, while praise detection is more sensitive to both, reflecting the greater subjectivity of positive relational gestures. These findings lay the groundwork for integrating LLM-based relational annotation into sign prediction pipelines.

cs.SI↗

Layered Ego Networks in Email Communication: From Enron to the Jmail Archive

Email archives offer a rare view of social relationships through repeated communication, but it remains unclear how well classical ego network layering applies to digital interaction data. This paper compares two public email archives with sharply contrasting structures: Enron, a workplace corpus involving around 150 users, and Jmail, a single-ego archive centered on an exceptionally active focal actor whose communication volume is more than twenty times higher than the average Enron user. We ask, in each case, whether Dunbar-like layered organization is recoverable from email communication frequency and how it should be interpreted. For Jmail, we show that extreme communication intensity causes standard layering methods (whether clustering-based or threshold-based) to break down. Jmail is not a broad communication environment with many occasional contacts, but a selective pool of high-interest alters operating on a much higher frequency scale than ordinary email. Once the Dunbar frequency ladder is anchored to the empirical support-clique boundary, a clearer layered structure emerges. Reciprocity analysis confirms that the recovered layers reflect genuine bidirectional relationships rather than artifacts of the focal actor's outgoing activity. Enron serves as a workplace benchmark that grounds the comparison: its ego networks partially reproduce Dunbar-like organization, with stable inner circles and an outermost recovered layer corresponding to Dunbar's affinity group ($\sim50$), confirming that layered structure is recoverable from ordinary organizational email. Overall, the findings show that Dunbar-like organization can be meaningfully studied in email archives, but that selective high-frequency archives require frequency normalization before the layered structure becomes interpretable.

cs.SI↗

Operating Regimes of Decentralized Learning Under Mobility and Bandwidth Constraints

Decentralized learning is a promising paradigm for collaborative training in mobile and pervasive systems, as it avoids a central coordinator and does not require sharing raw data. Yet, most analyses rely on idealized communication assumptions that break down in wireless settings, where connectivity is intermittent, topology changes due to mobility, and bandwidth is limited. We study decentralized averaging under client asynchrony, time-varying contact graphs, and technology-dependent throughput constraints. We implement a fully decentralized protocol that overlaps synchronization with local training and supports partial tensor-level transfers when contacts end early. Using Random Waypoint mobility and multiple wireless technologies (Bluetooth LE, LTE, and Wi-Fi), we quantify how network dynamics and link capacity impact convergence. We identify three operating regimes: (i) inter-contact time largely dictates convergence via mixing, (ii) partial updates are often well tolerated when contacts are frequent, and (iii) very dense contact patterns can trigger contention, reducing effective throughput. These findings provide a practical lens to reason about decentralized learning deployments over realistic wireless systems, highlighting when improving connectivity, increasing bandwidth, or mitigating contention is most impactful.

cs.NI↗

Cascade-driven opinion dynamics on social networks

Online social networks (OSNs) have transformed the way individuals fulfill their social needs and consume information. As OSNs become increasingly prominent sources for news dissemination, individuals often encounter content that influences their opinions through both direct interactions and broader network dynamics. In this paper, we propose the Friedkin-Johnsen on Cascade (FJC) model, which is, to the best of our knowledge, is the first attempt to integrate information cascades and opinion dynamics, specifically using the very popular Friedkin-Johnsen model. Our model, validated over real social cascades, highlights how the convergence of socialization and sharing news on these platforms can disrupt opinion evolution dynamics typically observed in offline settings. Our findings demonstrate that these cascades can amplify the influence of central opinion leaders, making them more resistant to divergent viewpoints, even when challenged by a critical mass of dissenting opinions. This research underscores the importance of understanding the interplay between social dynamics and information flow in shaping public discourse in the digital age.

cs.SI↗

DecHW: Heterogeneous Decentralized Federated Learning Exploiting Second-Order Information

Decentralized Federated Learning (DFL) is a serverless collaborative machine learning paradigm where devices collaborate directly with neighbouring devices to exchange model information for learning a generalized model. However, variations in individual experiences and different levels of device interactions lead to data and model initialization heterogeneities across devices. Such heterogeneities leave variations in local model parameters across devices that leads to slower convergence. This paper tackles the data and model heterogeneity by explicitly addressing the parameter level varying evidential credence across local models. A novel aggregation approach is introduced that captures these parameter variations in local models and performs robust aggregation of neighbourhood local updates. Specifically, consensus weights are generated via approximation of second-order information of local models on their local datasets. These weights are utilized to scale neighbourhood updates before aggregating them into global neighbourhood representation. In extensive experiments with computer vision tasks, the proposed approach shows strong generalizability of local models at reduced communication costs.

cs.LG↗

Sparing User Time with a Socially-Aware Independent Metaverse Avatar

The Metaverse is redefining digital interactions by merging physical, virtual, and social dimensions, yet its effects on social networking remain largely unexplored. This work examines the role of independent avatars (autonomous digital entities capable of managing social interactions on behalf of users), to optimize social time allocation and reshape Metaverse-based Online Social Networks. We propose a novel computational model that integrates a quantitative and realistic representation of user social life, grounded in evolutionary anthropology, with a framework for avatar-mediated interactions. Our model quantifies the effectiveness of a partial replacement of in-person interactions with independent avatar interactions. Additionally, it accounts for social conflicts and specific socialization constraints. We leverage our model to explore the benefits and trade-offs of an avatar-augmented social life in the Metaverse. Since the exact problem formulation leads to an NP-hard optimization problem when incorporating avatars into the social network, we tackle this challenge by introducing a heuristic solution. Through simulations, we compare avatar-mediated and non-avatar-mediated social networking, demonstrating the potential of independent avatars to enhance social connectivity and efficiency. Our findings provide a foundation for optimizing Metaverse-based social interactions, as well as useful insights for future digital social network design.

cs.SI↗

Mind Reading or Misreading? LLMs on the Big Five Personality Test

We evaluate large language models (LLMs) for automatic personality prediction from text under the binary Five Factor Model (BIG5). Five models -- including GPT-4 and lightweight open-source alternatives -- are tested across three heterogeneous datasets (Essays, MyPersonality, Pandora) and two prompting strategies (minimal vs. enriched with linguistic and psychological cues). Enriched prompts reduce invalid outputs and improve class balance, but also introduce a systematic bias toward predicting trait presence. Performance varies substantially: Openness and Agreeableness are relatively easier to detect, while Extraversion and Neuroticism remain challenging. Although open-source models sometimes approach GPT-4 and prior benchmarks, no configuration yields consistently reliable predictions in zero-shot binary settings. Moreover, aggregate metrics such as accuracy and macro-F1 mask significant asymmetries, with per-class recall offering clearer diagnostic value. These findings show that current out-of-the-box LLMs are not yet suitable for APPT, and that careful coordination of prompt design, trait framing, and evaluation metrics is essential for interpretable results.

cs.CL↗

DODO: Causal Structure Learning with Budgeted Interventions

Artificial Intelligence has achieved remarkable advancements in recent years, yet much of its progress relies on identifying increasingly complex correlations. Enabling causality awareness in AI has the potential to enhance its performance by enabling a deeper understanding of the underlying mechanisms of the environment. In this paper, we introduce DODO, an algorithm defining how an Agent can autonomously learn the causal structure of its environment through repeated interventions. We assume a scenario where an Agent interacts with a world governed by a causal Directed Acyclic Graph (DAG), which dictates the system's dynamics but remains hidden from the Agent. The Agent's task is to accurately infer the causal DAG, even in the presence of noise. To achieve this, the Agent performs interventions, leveraging causal inference techniques to analyze the statistical significance of observed changes. Results show better performance for DODO, compared to observational approaches, in all but the most limited resource conditions. DODO is often able to reconstruct with as low as zero errors the structure of the causal graph. In the most challenging configuration, DODO outperforms the best baseline by +0.25 F1 points.

cs.AI↗

On the Joint Effect of Culture and Discussion Topics on X (Twitter) Signed Ego Networks

Humans are known to structure social relationships according to certain patterns, such as the Ego Network Model (ENM). These patterns result from our innate cognitive limits and can therefore be observed in the vast majority of large human social groups. Until recently, the main focus of research was the structural characteristics of this model. The main aim of this paper is to complement previous findings with systematic and data-driven analyses on the positive and negative sentiments of social relationships, across different cultures, communities and topics of discussion. A total of 26 datasets were collected for this work. It was found that contrary to previous findings, the influence of culture is not easily ``overwhelmed'' by that of the topic of discussion. However, more specific and polarising topics do lead to noticeable increases in negativity across all cultures. These negativities also appear to be stable across the different levels of the ENM, which contradicts previous hypotheses. Finally, the number of generic topics being discussed between users seems to be a good predictor of the overall positivity of their relationships.

cs.SI↗

Robustness of Decentralised Learning to Nodes and Data Disruption

In the vibrant landscape of AI research, decentralised learning is gaining momentum. Decentralised learning allows individual nodes to keep data locally where they are generated and to share knowledge extracted from local data among themselves through an interactive process of collaborative refinement. This paradigm supports scenarios where data cannot leave local nodes due to privacy or sovereignty reasons or real-time constraints imposing proximity of models to locations where inference has to be carried out. The distributed nature of decentralised learning implies significant new research challenges with respect to centralised learning. Among them, in this paper, we focus on robustness issues. Specifically, we study the effect of nodes' disruption on the collective learning process. Assuming a given percentage of "central" nodes disappear from the network, we focus on different cases, characterised by (i) different distributions of data across nodes and (ii) different times when disruption occurs with respect to the start of the collaborative learning task. Through these configurations, we are able to show the non-trivial interplay between the properties of the network connecting nodes, the persistence of knowledge acquired collectively before disruption or lack thereof, and the effect of data availability pre- and post-disruption. Our results show that decentralised learning processes are remarkably robust to network disruption. As long as even minimum amounts of data remain available somewhere in the network, the learning process is able to recover from disruptions and achieve significant classification accuracy. This clearly varies depending on the remaining connectivity after disruption, but we show that even nodes that remain completely isolated can retain significant knowledge acquired before the disruption.

cs.LG↗

The Built-In Robustness of Decentralized Federated Averaging to Bad Data

Decentralized federated learning (DFL) enables devices to collaboratively train models over complex network topologies without relying on a central controller. In this setting, local data remains private, but its quality and quantity can vary significantly across nodes. The extent to which a fully decentralized system is vulnerable to poor-quality or corrupted data remains unclear, but several factors could contribute to potential risks. Without a central authority, there can be no unified mechanism to detect or correct errors, and each node operates with a localized view of the data distribution, making it difficult for the node to assess whether its perspective aligns with the true distribution. Moreover, models trained on low-quality data can propagate through the network, amplifying errors. To explore the impact of low-quality data on DFL, we simulate two scenarios with degraded data quality -- one where the corrupted data is evenly distributed in a subset of nodes and one where it is concentrated on a single node -- using a decentralized implementation of FedAvg. Our results reveal that averaging-based decentralized learning is remarkably robust to localized bad data, even when the corrupted data resides in the most influential nodes of the network. Counterintuitively, this robustness is further enhanced when the corrupted data is concentrated on a single node, regardless of its centrality in the communication network topology. This phenomenon is explained by the averaging process, which ensures that no single node -- however central -- can disproportionately influence the overall learning process.

cs.LG↗

The Impact of COVID-19 on Twitter Ego Networks: Structure, Sentiment, and Topics

Lockdown measures, implemented by governments during the initial phases of the COVID-19 pandemic to reduce physical contact and limit viral spread, imposed significant restrictions on in-person social interactions. Consequently, individuals turned to online social platforms to maintain connections. Ego networks, which model the organization of personal relationships according to human cognitive constraints on managing meaningful interactions, provide a framework for analyzing such dynamics. The disruption of physical contact and the predominant shift of social life online potentially altered the allocation of cognitive resources dedicated to managing these digital relationships. This research aims to investigate the impact of lockdown measures on the characteristics of online ego networks, presumably resulting from this reallocation of cognitive resources. To this end, a large dataset of Twitter users was examined, covering a seven-year period of activity. Analyzing a seven-year Twitter dataset -- including five years pre-pandemic and two years post -- we observe clear, though temporary, changes. During lockdown, ego networks expanded, social circles became more structured, and relationships intensified. Simultaneously, negative interactions increased, and users engaged with a broader range of topics, indicating greater thematic diversity. Once restrictions were lifted, these structural, emotional, and thematic shifts largely reverted to pre-pandemic norms -- suggesting a temporary adaptation to an extraordinary social context.

cs.SI↗

Initialisation and Network Effects in Decentralised Federated Learning

Fully decentralised federated learning enables collaborative training of individual machine learning models on a distributed network of communicating devices while keeping the training data localised on each node. This approach avoids central coordination, enhances data privacy and eliminates the risk of a single point of failure. Our research highlights that the effectiveness of decentralised federated learning is significantly influenced by the network topology of connected devices and the learning models' initial conditions. We propose a strategy for uncoordinated initialisation of the artificial neural networks based on the distribution of eigenvector centralities of the underlying communication network, leading to a radically improved training efficiency. Additionally, our study explores the scaling behaviour and the choice of environmental parameters under our proposed initialisation strategy. This work paves the way for more efficient and scalable artificial neural network training in a distributed and uncoordinated environment, offering a deeper understanding of the intertwining roles of network structure and learning dynamics.

cs.LG↗