arXiv subjects

Giuseppe Fenza

Publications and source records attributed to Giuseppe Fenza.

9 recordsLinked to original sources

arXiv2026

Digital Twins for Opinion Dynamics: A Generative LLM Framework for Social Networks

The study of opinion dynamics in social networks is one of the key challenges in computational social science with direct relevance to understanding political polarization, misinformation, and health responses. Current approaches focus on simplified mathematical models that ignore linguistic and contextual factors related to belief updates or use Large Language Model (LLM)-based simulations that have not been validated against real data. We present a framework based on the concept of a digital twin to simulate opinion dynamics in social networks. The approach fills the gap by cloning a real-world Twitter network, assigns a set of attributes for agents (such as persona, emotions, centrality, stubbornness, and influence), and employs Mistral-7B to perform opinion update based on memory and social exposure. To evaluate the proposed approach, we validate it against two real Twitter datasets (COVID-19 discourse and U.S elections 2020). The results show that the capability of the proposed framework reproduces opinion trajectories and reduces individual prediction error by more than 50% compared to the best-performing classical baseline (Mistral-7B achieves Mean Absolute Error (MAE) = 0.150 and 0.121 on the COVID-19 and US Election 2020 datasets, respectively). We observe similar improvements in structural alignment (Delta_r = 0.120 and 0.180) and polarization dynamics (Delta_Var = 0.106 and 0.115) on the two datasets, respectively. Additionally, the ablation studies confirm that agent attributes, memory, and social exposure all contribute to the framework's predictive fidelity in reproducing opinion trajectories, with agent attributes being the most critical contributor. Overall, our results demonstrate that grounding Mistral-7B within empirically cloned interaction networks produces a realistic simulation framework capable of reproducing complex social dynamics.

cs.LG↗

arXiv2026

Bias Amplification in Multi-Agent Network: How Biased Agents Shape Opinions and Rhetoric

Large language models (LLMs) are increasingly deployed in applications involving interaction between agents, where their output plays a role in collective reasoning and decision-making processes. Despite significant research into the functioning of LLMs in such multi-agent systems, the processes of bias propagation in such systems are still a challenge. This work studies how biased opinions are propagated in the form of textual interaction in an environment of LLMs, in which a minority of agents maintain persistent extreme opinions, while the remaining agents iteratively update their beliefs through structured textual interactions. The findings show that even the presence of a small percentage of biased agents in such a system leads to significant shifts in the opinions of non-biased agents. It suggests that for the same percentage of biased agents, the shifts occur more quickly for the Llama~3.2 model when compared to a classical Friedkin-Johnsen (FJ) model. Further semantic analysis demonstrates that rhetorical consistency in textual explanations increases systematically with biased exposure and, importantly, is partially decoupled from numerical convergenumericalutral agents adopt the vocabulary employed by the biased agents even in configurations where their numerical opinion shifts remain moderate. The research helps explain how bias and language develop together in multi-agent language model ecosystems.

cs.LG↗

arXiv2026

Digital Persuasion: Understanding the Impact of Online Influencers on Public Opinion

The studying of opinion dynamics and its propagation within social networks is crucial for addressing a wide range of challenges, including political polarization, public health, and marketing strategies. In this work, we study the problem of opinion dynamics by proposing a framework based on Friedkin-Johnsen (FJ) to identifies influential users and study their impact on dynamics opinions of community. The FJ model assume each individual have two opinions: initial and expressed. Through a series of initial opinion manipulation experiments, the proposed framework assesses the impact of influential versus random users on the overall community opinion. The proposed framework is validated using a tweet dataset representing the U.S. presidential election. The results shows that influencers with highest influencing score, significantly shift the overall community opinion. Moreover, the results shows that the impact of influencers not limited to direct neighbors , but beyond it, to their neighbors of neighbors . This study demonstrates how digital influencers on social media can shape public opinion regarding a subject or cause.

cs.SI↗

arXiv2026

Quantization-Triggered Backdoors in Language Models: Cross-Quantizer Transferability and the Validation--Deployment Gap

Post-training quantization is often treated as a semantically neutral optimization for edge deployment of Large Language Models. When a full-precision source checkpoint is evaluated and quantization is applied downstream without equivalent re-evaluation, this workflow creates a structural validation--deployment gap: because quantization is a many-to-one mapping over parameter space, source-precision certification does not guarantee behavioral equivalence in the deployed configuration. We formalize this gap through Quantization Behavioral Equivalence Classes (QBECs) and prove that QBEC membership does not imply behavioral equivalence, providing a theoretical basis for quantization-triggered backdoor attacks. Building on a three-stage adversarial fine-tuning framework, we embed latent malicious payloads into models that satisfy the source-precision checks used in our evaluation, yet activate targeted adversarial behavior upon INT8 or 4-bit compression. We evaluate this threat in two operationally motivated scenarios, tactical machine translation and political content analysis, extending prior work from decoder-only causal LMs to multilingual encoder-decoder sequence-to-sequence models. Results show that backdoored translation models move from zero measured friend--foe corruption at repaired FP16 to up to 85.02% inversion after quantization, and that a paired stance classifier measures an ideological shift of up to $Δ\mathrm{Bias}=0.33$ upon compression. A cross-quantizer transferability analysis further shows that attack persistence varies across quantization schemes and model architectures, rather than being determined by nominal bit-width alone. These findings demonstrate that source-precision auditing alone does not rule out quantization-triggered behavior and that the final deployed configuration must be included in behavioral certification for trustworthy edge AI.

cs.LG↗

arXiv2021

Distributed Smart Measurement Architecture for Industrial Automation

Cyber-Physical Systems (CPSs) employed for Industrial Automation often require the adoption of a hybrid data processing approach mediating between cloud, edge, and fog computing paradigms. Nowadays, it is possible to shift data pre-processing capabilities closer to data sensing to collect environmental measurements locally on the edge or deep edge. In line with the emerging computing paradigms, this work proposes a solution that includes both software and hardware components and which simplifies the deployment of smart measurement systems. The solution stresses also the adoption of standards and open data paradigms for simplifying the integration and ensuring the interoperability of all the systems involved. The distributed smart measurement solution has been adopted in an Industry Automation use case included in the project Cyber-Physical Systems for Europe (CPS4EU). The use case attains with monitoring of an industrial trimming machine operating in the production process of a big part of a civil aircraft, where the sensing and processing capabilities of the distributed smart measurement system allow to collect different parameters of work parts to satisfy the expected quality of the production process.

cs.SE↗

arXiv2020

Implementing the Cognition Level for Industry 4.0 by integrating Augmented Reality and Manufacturing Execution Systems

In the current industrial practices, the exponential growth in terms of availability and affordability of sensors, data acquisition systems, and computer networks forces factories to move toward implementing high integrating Cyber-Physical Systems (CPS) with production, logistics, and services. This transforms today's factories into Industry 4.0 factories with significant economic potential. Industry 4.0, also known as the fourth Industrial Revolution, levers on the integration of cyber technologies, the Internet of Things, and Services. This paper proposes an Augmented Reality (AR)-based system that creates a Cognition Level that integrates existent Manufacturing Execution Systems (MES) to CPS. The idea is to highlight the opportunities offered by AR technologies to CPS by describing an application scenario. The system, analyzed in a real factory, shows its capacity to integrate physical and digital worlds strongly. Furthermore, the conducted survey (based on the Situation Awareness Global Assessment Technique method) reveals significant advantages in terms of production monitoring, progress, and workers' Situation Awareness in general.

cs.CY↗

arXiv2020

Semantic CPPS in Industry 4.0

Cyber-Physical Systems (CPS) play a crucial role in the era of the 4thIndustrial Revolution. Recently, the application of the CPS to industrial manufacturing leads to a specialization of them referred as Cyber-Physical Production Systems (CPPS). Among other challenges, CPS and CPPS should be able to address interoperability issues, since one of their intrinsic requirement is the capability to interface and cooperate with other systems. On the other hand, to fully realize theIndustry 4.0 vision, it is required to address horizontal, vertical, and end-to-end integration enabling a complete awareness through the entire supply chain. In this context, Semantic Web standards and technologies may have a promising role to represent manufacturing knowledge in a machine-interpretable way for enabling communications among heterogeneous Industrial assets. This paper proposes an integration of Semantic Web models available at state of the art for implementing a5C architecture mainly targeted to collect and process semantic data stream in a way that would unlock the potentiality of data yield in a smart manufacturing environment. The analysis of key industrial ontologies and semantic technologies allows us to instantiate an example scenario for monitoring Overall Equipment Effectiveness(OEE). The solution uses the SOSA ontology for representing the semantic datastream. Then, C-SPARQL queries are defined for periodically carrying out useful KPIs to address the proposed aim.

cs.AI↗

arXiv2020

A Cognitive Approach based on the Actionable Knowledge Graph for supporting Maintenance Operations

In the era of Industry 4.0, cognitive computing and its enabling technologies (Artificial Intelligence, Machine Learning, etc.) allow to define systems able to support maintenance by providing relevant information, at the right time, retrieved from structured companies' databases, and unstructured documents, like technical manuals, intervention reports, and so on. Moreover, contextual information plays a crucial role in tailoring the support both during the planning and the execution of interventions. Contextual information can be detected with the help of sensors, wearable devices, indoor and outdoor positioning systems, and object recognition capabilities (using fixed or wearable cameras), all of which can collect historical data for further analysis. In this work, we propose a cognitive system that learns from past interventions to generate contextual recommendations for improving maintenance practices in terms of time, budget, and scope. The system uses formal conceptual models, incremental learning, and ranking algorithms to accomplish these objectives.

cs.LG↗

arXiv2015

Time Aware Knowledge Extraction for Microblog Summarization on Twitter

Microblogging services like Twitter and Facebook collect millions of user generated content every moment about trending news, occurring events, and so on. Nevertheless, it is really a nightmare to find information of interest through the huge amount of available posts that are often noise and redundant. In general, social media analytics services have caught increasing attention from both side research and industry. Specifically, the dynamic context of microblogging requires to manage not only meaning of information but also the evolution of knowledge over the timeline. This work defines Time Aware Knowledge Extraction (briefly TAKE) methodology that relies on temporal extension of Fuzzy Formal Concept Analysis. In particular, a microblog summarization algorithm has been defined filtering the concepts organized by TAKE in a time-dependent hierarchy. The algorithm addresses topic-based summarization on Twitter. Besides considering the timing of the concepts, another distinguish feature of the proposed microblog summarization framework is the possibility to have more or less detailed summary, according to the user's needs, with good levels of quality and completeness as highlighted in the experimental results.

cs.IR↗