-
Generative AI collective behavior needs an interactionist paradigm
Authors:
Laura Ferrarotti,
Gian Maria Campedelli,
Roberto Dessì,
Andrea Baronchelli,
Giovanni Iacca,
Kathleen M. Carley,
Alex Pentland,
Joel Z. Leibo,
James Evans,
Bruno Lepri
Abstract:
In this article, we argue that understanding the collective behavior of agents based on large language models (LLMs) is an essential area of inquiry, with important implications in terms of risks and benefits, impacting us as a society at many levels. We claim that the distinctive nature of LLMs--namely, their initialization with extensive pre-trained knowledge and implicit social priors, together…
▽ More
In this article, we argue that understanding the collective behavior of agents based on large language models (LLMs) is an essential area of inquiry, with important implications in terms of risks and benefits, impacting us as a society at many levels. We claim that the distinctive nature of LLMs--namely, their initialization with extensive pre-trained knowledge and implicit social priors, together with their capability of adaptation through in-context learning--motivates the need for an interactionist paradigm consisting of alternative theoretical foundations, methodologies, and analytical tools, in order to systematically examine how prior knowledge and embedded values interact with social context to shape emergent phenomena in multi-agent generative AI systems. We propose and discuss four directions that we consider crucial for the development and deployment of LLM-based collectives, focusing on theory, methods, and trans-disciplinary dialogue.
△ Less
Submitted 15 January, 2026;
originally announced January 2026.
-
A Criminology of Machines
Authors:
Gian Maria Campedelli
Abstract:
While the possibility of reaching human-like Artificial Intelligence (AI) remains controversial, the likelihood that the future will be characterized by a society with a growing presence of autonomous machines is high. Autonomous AI agents are already deployed and active across several industries and digital environments and alongside human-human and human-machine interactions, machine-machine int…
▽ More
While the possibility of reaching human-like Artificial Intelligence (AI) remains controversial, the likelihood that the future will be characterized by a society with a growing presence of autonomous machines is high. Autonomous AI agents are already deployed and active across several industries and digital environments and alongside human-human and human-machine interactions, machine-machine interactions are poised to become increasingly prevalent. Given these developments, I argue that criminology must begin to address the implications of this transition for crime and social control. Drawing on Actor-Network Theory and Woolgar's decades-old call for a sociology of machines -- frameworks that acquire renewed relevance with the rise of generative AI agents -- I contend that criminologists should move beyond conceiving AI solely as a tool. Instead, AI agents should be recognized as entities with agency encompassing computational, social, and legal dimensions. Building on the literature on AI safety, I thus examine the risks associated with the rise of multi-agent AI systems, proposing a dual taxonomy to characterize the channels through which interactions among AI agents may generate deviant, unlawful, or criminal outcomes. I then advance and discuss four key questions that warrant theoretical and empirical attention: (1) Can we assume that machines will simply mimic humans? (2) Will crime theories developed for humans suffice to explain deviant or criminal behaviors emerging from interactions between autonomous AI agents? (3) What types of criminal behaviors will be affected first? (4) How might this unprecedented societal shift impact policing? These questions underscore the urgent need for criminologists to theoretically and empirically engage with the implications of multi-agent AI systems for the study of crime and play a more active role in debates on AI safety and governance.
△ Less
Submitted 6 November, 2025; v1 submitted 4 November, 2025;
originally announced November 2025.
-
CrisiText: A dataset of warning messages for LLM training in emergency communication
Authors:
Giacomo Gonella,
Gian Maria Campedelli,
Stefano Menini,
Marco Guerini
Abstract:
Effectively identifying threats and mitigating their potential damage during crisis situations, such as natural disasters or violent attacks, is paramount for safeguarding endangered individuals. To tackle these challenges, AI has been used in assisting humans in emergency situations. Still, the use of NLP techniques remains limited and mostly focuses on classification tasks. The significant poten…
▽ More
Effectively identifying threats and mitigating their potential damage during crisis situations, such as natural disasters or violent attacks, is paramount for safeguarding endangered individuals. To tackle these challenges, AI has been used in assisting humans in emergency situations. Still, the use of NLP techniques remains limited and mostly focuses on classification tasks. The significant potential of timely warning message generation using NLG architectures, however, has been largely overlooked. In this paper we present CrisiText, the first large-scale dataset for the generation of warning messages across 13 different types of crisis scenarios. The dataset contains more than 400,000 warning messages (spanning almost 18,000 crisis situations) aimed at assisting civilians during and after such events. To generate the dataset, we started from existing crisis descriptions and created chains of events related to the scenarios. Each event was then paired with a warning message. The generations follow experts' written guidelines to ensure correct terminology and factuality of their suggestions. Additionally, each message is accompanied by three suboptimal warning types to allow for the study of different NLG approaches. To this end, we conducted a series of experiments comparing supervised fine-tuning setups with preference alignment, zero-shot, and few-shot approaches. We further assessed model performance in out-of-distribution scenarios and evaluated the effectiveness of an automatic post-editor.
△ Less
Submitted 13 October, 2025; v1 submitted 10 October, 2025;
originally announced October 2025.
-
Deep Learning for Crime Forecasting: The Role of Mobility at Fine-grained Spatiotemporal Scales
Authors:
Ariadna Albors Zumel,
Michele Tizzoni,
Gian Maria Campedelli
Abstract:
Objectives: To develop a deep learning framework to evaluate if and how incorporating micro-level mobility features, alongside historical crime and sociodemographic data, enhances predictive performance in crime forecasting at fine-grained spatial and temporal resolutions.
Methods: We advance the literature on computational methods and crime forecasting by focusing on four U.S. cities (i.e., Bal…
▽ More
Objectives: To develop a deep learning framework to evaluate if and how incorporating micro-level mobility features, alongside historical crime and sociodemographic data, enhances predictive performance in crime forecasting at fine-grained spatial and temporal resolutions.
Methods: We advance the literature on computational methods and crime forecasting by focusing on four U.S. cities (i.e., Baltimore, Chicago, Los Angeles, and Philadelphia). We employ crime incident data obtained from each city's police department, combined with sociodemographic data from the American Community Survey and human mobility data from Advan, collected from 2019 to 2023. This data is aggregated into grids with equally sized cells of 0.077 sq. miles (0.2 sq. kms) and used to train our deep learning forecasting model, a Convolutional Long Short-Term Memory (ConvLSTM) network, which predicts crime occurrences 12 hours ahead using 14-day and 2-day input sequences. We also compare its performance against three baseline models: logistic regression, random forest, and standard LSTM.
Results: Incorporating mobility features improves predictive performance, especially when using shorter input sequences. Noteworthy, however, the best results are obtained when both mobility and sociodemographic features are used together, with our deep learning model achieving the highest recall, precision, and F1 score in all four cities, outperforming alternative methods. With this configuration, longer input sequences enhance predictions for violent crimes, while shorter sequences are more effective for property crimes.
Conclusion: These findings underscore the importance of integrating diverse data sources for spatiotemporal crime forecasting, mobility included. They also highlight the advantages (and limits) of deep learning when dealing with fine-grained spatial and temporal scales.
△ Less
Submitted 25 September, 2025;
originally announced September 2025.
-
I Want to Break Free! Persuasion and Anti-Social Behavior of LLMs in Multi-Agent Settings with Social Hierarchy
Authors:
Gian Maria Campedelli,
Nicolò Penzo,
Massimo Stefan,
Roberto Dessì,
Marco Guerini,
Bruno Lepri,
Jacopo Staiano
Abstract:
As LLM-based agents become increasingly autonomous and will more freely interact with each other, studying the interplay among them becomes crucial to anticipate emergent phenomena and potential risks. In this work, we provide an in-depth analysis of the interactions among agents within a simulated hierarchical social environment, drawing inspiration from the Stanford Prison Experiment. Leveraging…
▽ More
As LLM-based agents become increasingly autonomous and will more freely interact with each other, studying the interplay among them becomes crucial to anticipate emergent phenomena and potential risks. In this work, we provide an in-depth analysis of the interactions among agents within a simulated hierarchical social environment, drawing inspiration from the Stanford Prison Experiment. Leveraging 2,400 conversations across six LLMs (i.e., LLama3, Orca2, Command-r, Mixtral, Mistral2, and gpt4.1) and 240 experimental scenarios, we analyze persuasion and anti-social behavior between a guard and a prisoner agent with differing objectives. We first document model-specific conversational failures in this multi-agent power dynamic context, thereby narrowing our analytic sample to 1,600 conversations. Among models demonstrating successful interaction, we find that goal setting significantly influences persuasiveness but not anti-social behavior. Moreover, agent personas, especially the guard's, substantially impact both successful persuasion by the prisoner and the manifestation of anti-social actions. Notably, we observe the emergence of anti-social conduct even in absence of explicit negative personality prompts. These results have important implications for the development of interactive LLM agents and the ongoing discussion of their societal impact.
△ Less
Submitted 4 November, 2025; v1 submitted 9 October, 2024;
originally announced October 2024.
-
Inequality, Crime and Public Health: A Survey of Emerging Trends in Urban Data Science
Authors:
Massimiliano Luca,
Gian Maria Campedelli,
Simone Centellegher,
Michele Tizzoni,
Bruno Lepri
Abstract:
Urban agglomerations are constantly and rapidly evolving ecosystems, with globalization and increasing urbanization posing new challenges in sustainable urban development well summarized in the United Nations' Sustainable Development Goals (SDGs). The advent of the digital age generated by modern alternative data sources provides new tools to tackle these challenges with spatio-temporal scales tha…
▽ More
Urban agglomerations are constantly and rapidly evolving ecosystems, with globalization and increasing urbanization posing new challenges in sustainable urban development well summarized in the United Nations' Sustainable Development Goals (SDGs). The advent of the digital age generated by modern alternative data sources provides new tools to tackle these challenges with spatio-temporal scales that were previously unavailable with census statistics. In this review, we present how new digital data sources are employed to provide data-driven insights to study and track (i) urban crime and public safety; (ii) socioeconomic inequalities and segregation; and (iii) public health, with a particular focus on the city scale.
△ Less
Submitted 15 December, 2022;
originally announced December 2022.
-
Explainable Machine Learning for Predicting Homicide Clearance in the United States
Authors:
Gian Maria Campedelli
Abstract:
Purpose: To explore the potential of Explainable Machine Learning in the prediction and detection of drivers of cleared homicides at the national- and state-levels in the United States.
Methods: First, nine algorithmic approaches are compared to assess the best performance in predicting cleared homicides country-wise, using data from the Murder Accountability Project. The most accurate algorithm…
▽ More
Purpose: To explore the potential of Explainable Machine Learning in the prediction and detection of drivers of cleared homicides at the national- and state-levels in the United States.
Methods: First, nine algorithmic approaches are compared to assess the best performance in predicting cleared homicides country-wise, using data from the Murder Accountability Project. The most accurate algorithm among all (XGBoost) is then used for predicting clearance outcomes state-wise. Second, SHAP, a framework for Explainable Artificial Intelligence, is employed to capture the most important features in explaining clearance patterns both at the national and state levels.
Results: At the national level, XGBoost demonstrates to achieve the best performance overall. Substantial predictive variability is detected state-wise. In terms of explainability, SHAP highlights the relevance of several features in consistently predicting investigation outcomes. These include homicide circumstances, weapons, victims' sex and race, as well as number of involved offenders and victims.
Conclusions: Explainable Machine Learning demonstrates to be a helpful framework for predicting homicide clearance. SHAP outcomes suggest a more organic integration of the two theoretical perspectives emerged in the literature. Furthermore, jurisdictional heterogeneity highlights the importance of developing ad hoc state-level strategies to improve police performance in clearing homicides.
△ Less
Submitted 9 March, 2022;
originally announced March 2022.
-
Multi-modal Networks Reveal Patterns of Operational Similarity of Terrorist Organizations
Authors:
Gian Maria Campedelli,
Iain J. Cruickshank,
Kathleen M. Carley
Abstract:
Capturing dynamics of operational similarity among terrorist groups is critical to provide actionable insights for counter-terrorism and intelligence monitoring. Yet, in spite of its theoretical and practical relevance, research addressing this problem is currently lacking. We tackle this problem proposing a novel computational framework for detecting clusters of terrorist groups sharing similar b…
▽ More
Capturing dynamics of operational similarity among terrorist groups is critical to provide actionable insights for counter-terrorism and intelligence monitoring. Yet, in spite of its theoretical and practical relevance, research addressing this problem is currently lacking. We tackle this problem proposing a novel computational framework for detecting clusters of terrorist groups sharing similar behaviors, focusing on groups' yearly repertoire of deployed tactics, attacked targets, and utilized weapons. Specifically considering those organizations that have plotted at least 50 attacks from 1997 to 2018, accounting for a total of 105 groups responsible for more than 42,000 events worldwide, we offer three sets of results. First, we show that over the years global terrorism has been characterized by increasing operational cohesiveness. Second, we highlight that year-to-year stability in co-clustering among groups has been particularly high from 2009 to 2018, indicating temporal consistency of similarity patterns in the last decade. Third, we demonstrate that operational similarity between two organizations is driven by three factors: (a) their overall activity; (b) the difference in the diversity of their operational repertoires; (c) the difference in a combined measure of diversity and activity. Groups' operational preferences, geographical homophily and ideological affinity have no consistent role in determining operational similarity.
△ Less
Submitted 15 December, 2021;
originally announced December 2021.
-
Learning future terrorist targets through temporal meta-graphs
Authors:
Gian Maria Campedelli,
Mihovil Bartulovic,
Kathleen M. Carley
Abstract:
In the last 20 years, terrorism has led to hundreds of thousands of deaths and massive economic, political, and humanitarian crises in several regions of the world. Using real-world data on attacks occurred in Afghanistan and Iraq from 2001 to 2018, we propose the use of temporal meta-graphs and deep learning to forecast future terrorist targets. Focusing on three event dimensions, i.e., employed…
▽ More
In the last 20 years, terrorism has led to hundreds of thousands of deaths and massive economic, political, and humanitarian crises in several regions of the world. Using real-world data on attacks occurred in Afghanistan and Iraq from 2001 to 2018, we propose the use of temporal meta-graphs and deep learning to forecast future terrorist targets. Focusing on three event dimensions, i.e., employed weapons, deployed tactics and chosen targets, meta-graphs map the connections among temporally close attacks, capturing their operational similarities and dependencies. From these temporal meta-graphs, we derive 2-day-based time series that measure the centrality of each feature within each dimension over time. Formulating the problem in the context of the strategic behavior of terrorist actors, these multivariate temporal sequences are then utilized to learn what target types are at the highest risk of being chosen. The paper makes two contributions. First, it demonstrates that engineering the feature space via temporal meta-graphs produces richer knowledge than shallow time-series that only rely on frequency of feature occurrences. Second, the performed experiments reveal that bi-directional LSTM networks achieve superior forecasting performance compared to other algorithms, calling for future research aiming at fully discovering the potential of artificial intelligence to counter terrorist violence.
△ Less
Submitted 21 April, 2021;
originally announced April 2021.
-
Temporal Clustering of Disorder Events During the COVID-19 Pandemic
Authors:
Gian Maria Campedelli,
Maria Rita D'Orsogna
Abstract:
The COVID-19 pandemic has unleashed multiple public health, socio-economic, and institutional crises. Measures taken to slow the spread of the virus have fostered significant strain between authorities and citizens, leading to waves of social unrest and anti-government demonstrations. We study the temporal nature of pandemic-related disorder events as tallied by the "COVID-19 Disorder Tracker" ini…
▽ More
The COVID-19 pandemic has unleashed multiple public health, socio-economic, and institutional crises. Measures taken to slow the spread of the virus have fostered significant strain between authorities and citizens, leading to waves of social unrest and anti-government demonstrations. We study the temporal nature of pandemic-related disorder events as tallied by the "COVID-19 Disorder Tracker" initiative by focusing on the three countries with the largest number of incidents, India, Israel, and Mexico. By fitting Poisson and Hawkes processes to the stream of data, we find that disorder events are inter-dependent and self-excite in all three countries. Geographic clustering confirms these features at the subnational level, indicating that nationwide disorders emerge as the convergence of meso-scale patterns of self-excitation. Considerable diversity is observed among countries when computing correlations of events between subnational clusters; these are discussed in the context of specific political, societal and geographic characteristics. Israel, the most territorially compact and where large scale protests were coordinated in response to government lockdowns, displays the largest reactivity and the shortest period of influence following an event, as well as the strongest nationwide synchrony. In Mexico, where complete lockdown orders were never mandated, reactivity and nationwide synchrony are lowest. Our work highlights the need for authorities to promote local information campaigns to ensure that livelihoods and virus containment policies are not perceived as mutually exclusive.
△ Less
Submitted 23 April, 2021; v1 submitted 16 January, 2021;
originally announced January 2021.
-
A Policy-oriented Agent-based Model of Recruitment into Organized Crime
Authors:
Gian Maria Campedelli,
Francesco Calderoni,
Mario Paolucci,
Tommaso Comunale,
Daniele Vilone,
Federico Cecconi,
Giulia Andrighetto
Abstract:
Criminal organizations exploit their presence on territories and local communities to recruit new workforce in order to carry out their criminal activities and business. The ability to attract individuals is crucial for maintaining power and control over the territories in which these groups are settled. This study proposes the formalization, development and analysis of an agent-based model (ABM)…
▽ More
Criminal organizations exploit their presence on territories and local communities to recruit new workforce in order to carry out their criminal activities and business. The ability to attract individuals is crucial for maintaining power and control over the territories in which these groups are settled. This study proposes the formalization, development and analysis of an agent-based model (ABM) that simulates a neighborhood of Palermo (Sicily) with the aim to understand the pathways that lead individuals to recruitment into organized crime groups (OCGs). Using empirical data on social, economic and criminal conditions of the area under analysis, we use a multi-layer network approach to simulate this scenario. As the final goal, we test different policies to counter recruitment into OCGs. These scenarios are based on two different dimensions of prevention and intervention: (i) primary and secondary socialization and (ii) law enforcement targeting strategies.
△ Less
Submitted 10 January, 2020;
originally announced January 2020.
-
A Complex Networks Approach to Find Latent Clusters of Terrorist Groups
Authors:
Gian Maria Campedelli,
Iain Cruickshank,
Kathleen M. Carley
Abstract:
Given the extreme heterogeneity of actors and groups participating in terrorist actions, investigating and assessing their characteristics can be important to extract relevant information and enhance the knowledge on their behaviors. The present work will seek to achieve this goal via a complex networks approach. This approach will allow finding latent clusters of similar terror groups using infor…
▽ More
Given the extreme heterogeneity of actors and groups participating in terrorist actions, investigating and assessing their characteristics can be important to extract relevant information and enhance the knowledge on their behaviors. The present work will seek to achieve this goal via a complex networks approach. This approach will allow finding latent clusters of similar terror groups using information on their operational characteristics. Specifically, using open access data of terrorist attacks occurred worldwide from 1997 to 2016, we build a multi-partite network that includes terrorist groups and related information on tactics, weapons, targets, active regions. We propose a novel algorithm for cluster formation that expands our earlier work that solely used Gower's coefficient of similarity via the application of Von Neumann entropy for mode-weighting. This novel approach is compared with our previous Gower-based method and a heuristic clustering technique that only focuses on groups' ideologies. The comparative analysis demonstrates that the entropy-based approach tends to reliably reflect the structure of the data that naturally emerges from the baseline Gower-based method. Additionally, it provides interesting results in terms of behavioral and ideological characteristics of terrorist groups. We furthermore show that the ideology-based procedure tends to distort or hide existing patterns. Among the main statistical results, our work reveals that groups belonging to opposite ideologies can share very common behaviors and that Islamist/jihadist groups hold peculiar behavioral characteristics with respect to the others. Limitations and potential work directions are also discussed, introducing the idea of a dynamic entropy-based framework.
△ Less
Submitted 10 January, 2020;
originally announced January 2020.
-
Where Are We? Using Scopus to Map the Literature at the Intersection Between Artificial Intelligence and Research on Crime
Authors:
Gian Maria Campedelli
Abstract:
Research on Artificial Intelligence (AI) applications has spread over many scientific disciplines. Scientists have tested the power of intelligent algorithms developed to predict (or learn from) natural, physical and social phenomena. This also applies to crime-related research problems. Nonetheless, studies that map the current state of the art at the intersection between AI and crime are lacking…
▽ More
Research on Artificial Intelligence (AI) applications has spread over many scientific disciplines. Scientists have tested the power of intelligent algorithms developed to predict (or learn from) natural, physical and social phenomena. This also applies to crime-related research problems. Nonetheless, studies that map the current state of the art at the intersection between AI and crime are lacking. What are the current research trends in terms of topics in this area? What is the structure of scientific collaboration when considering works investigating criminal issues using machine learning, deep learning, and AI in general? What are the most active countries in this specific scientific sphere? Using data retrieved from the Scopus database, this work quantitatively analyzes 692 published works at the intersection between AI and crime employing network science to respond to these questions. Results show that researchers are mainly focusing on cyber-related criminal topics and that relevant themes such as algorithmic discrimination, fairness, and ethics are considerably overlooked. Furthermore, data highlight the extremely disconnected structure of co-authorship networks. Such disconnectedness may represent a substantial obstacle to a more solid community of scientists interested in these topics. Additionally, the graph of scientific collaboration indicates that countries that are more prone to engage in international partnerships are generally less central in the network. This means that scholars working in highly productive countries (e.g. the United States, China) tend to mostly collaborate domestically. Finally, current issues and future developments within this scientific area are also discussed.
△ Less
Submitted 6 August, 2020; v1 submitted 23 December, 2019;
originally announced December 2019.