arXiv subjects

Stefano Maria Iacus

Publications and source records attributed to Stefano Maria Iacus.

At least 19 recordsLinked to original sources

arXiv2026

Spatial Heterogeneity in Climate Risk and Human Flourishing: An Exploration with Generative AI

Recent advances in Generative Artificial Intelligence (AI), particularly Large Language Models (LLMs), enable scalable extraction of spatial information from unstructured text and offer new methodological opportunities for studying climate geography. This study develops a spatial framework to examine how cumulative climate risk relates to multidimensional human flourishing across U.S. counties. High-resolution climate hazard indicators are integrated with a Human Flourishing Geographic Index (HFGI), an index derived from classification of 2.6 billion geotagged tweets using fine-tuned open-source Large Language Models (LLMs). These indicators are aggregated to the US county-level and mapped to a structural equation model to infer overall climate risk and human flourishing dimensions, including expressed well-being, meaning and purpose, social connectedness, psychological distress, physical condition, economic stability, religiosity, character and virtue, and institutional trust. The results reveal spatially heterogeneous associations between greater cumulative climate risk and lower levels of expressed human flourishing, with coherent spatial patterns corresponding to recurrent exposure to heat, flooding, wind, drought, and wildfire hazards. The study demonstrates how Generative AI can be combined with latent construct modeling for geographical analysis and for spatial knowledge extraction.

stat.AP↗

arXiv2025

Learning the Topic, Not the Language: How LLMs Classify Online Immigration Discourse Across Languages

Large language models (LLMs) offer new opportunities for scalable analysis of online discourse. Yet their use in multilingual social science research remains constrained by model size, cost and linguistic bias. We develop a lightweight, open-source LLM framework using fine-tuned LLaMA 3.2-3B models to classify immigration-related tweets across 13 languages. Unlike prior work relying on BERT style models or translation pipelines, we combine topic classification with stance detection and demonstrate that LLMs fine-tuned in just one or two languages can generalize topic understanding to unseen languages. Capturing ideological nuance, however, benefits from multilingual fine-tuning. Our approach corrects pretraining biases with minimal data from under-represented languages and avoids reliance on proprietary systems. With 26-168x faster inference and over 1000x cost savings compared to commercial LLMs, our method supports real-time analysis of billions of tweets. This scale-first framework enables inclusive, reproducible research on public attitudes across linguistic and cultural contexts.

cs.CL↗

arXiv2025

Two Americas of Well-Being: Divergent Rural-Urban Patterns of Life Satisfaction and Happiness from 2.6 B Social Media Posts

Using 2.6 billion geolocated social-media posts (2014-2022) and a fine-tuned generative language model, we construct county-level indicators of life satisfaction and happiness for the United States. We document an apparent rural-urban paradox: rural counties express higher life satisfaction while urban counties exhibit greater happiness. We reconcile this by treating the two as distinct layers of subjective well-being, evaluative vs. hedonic, showing that each maps differently onto place, politics, and time. Republican-leaning areas appear more satisfied in evaluative terms, but partisan gaps in happiness largely flatten outside major metros, indicating context-dependent political effects. Temporal shocks dominate the hedonic layer: happiness falls sharply during 2020-2022, whereas life satisfaction moves more modestly. These patterns are robust across logistic and OLS specifications and align with well-being theory. Interpreted as associations for the population of social-media posts, the results show that large-scale, language-based indicators can resolve conflicting findings about the rural-urban divide by distinguishing the type of well-being expressed, offering a transparent, reproducible complement to traditional surveys.

cs.SI↗

arXiv2024

Rethinking Scale: The Efficacy of Fine-Tuned Open-Source LLMs in Large-Scale Reproducible Social Science Research

Large Language Models (LLMs) are distinguished by their architecture, which dictates their parameter size and performance capabilities. Social scientists have increasingly adopted LLMs for text classification tasks, which are difficult to scale with human coders. While very large, closed-source models often deliver superior performance, their use presents significant risks. These include lack of transparency, potential exposure of sensitive data, challenges to replicability, and dependence on proprietary systems. Additionally, their high costs make them impractical for large-scale research projects. In contrast, open-source models, although available in various sizes, may underperform compared to commercial alternatives if used without further fine-tuning. However, open-source models offer distinct advantages: they can be run locally (ensuring data privacy), fine-tuned for specific tasks, shared within the research community, and integrated into reproducible workflows. This study demonstrates that small, fine-tuned open-source LLMs can achieve equal or superior performance to models such as ChatGPT-4. We further explore the relationship between training set size and fine-tuning efficacy in open-source models. Finally, we propose a hybrid workflow that leverages the strengths of both open and closed models, offering a balanced approach to performance, transparency, and reproducibility.

cs.CL↗

arXiv2022

Forecasting Change in Conflict Fatalities with Dynamic Elastic Net

This article illustrates an approach to forecasting change in conflict fatalities designed to address the complexity of the drivers and processes of armed conflicts. The design of this approach is based on two main choices. First, to account for the specificity of conflict drivers and processes over time and space, we model conflicts in each individual country separately. Second, we draw on an adaptive model -- Dynamic Elastic Net, DynENet -- which is able to efficiently select relevant predictors among a large set of covariates. We include over 700 variables in our models, adding event data on top of the data features provided by the con-venors of the forecasting competition. We show that our approach is suitable and computa-tionally efficient enough to address the complexity of conflict dynamics. Moreover, the adaptive nature of our model brings a significant added value. Because for each country our model only selects the variables that are relevant to predict conflict intensity, the retained predictors can be analyzed to describe the dynamic configuration of conflict drivers both across countries and within countries over time. Countries can then be clustered to observe the emergence of broader patterns related to correlates of conflict. In this sense, our ap-proach produces interpretable forecasts, addressing one key limitation of contemporary ap-proaches to forecasting.

stat.AP↗

arXiv2022

Compliance with restrictive measures during the COVID-19 pandemic in Europe: Does political partisanship influence behavioural responses?

The success of public health policies aimed at curtailing the COVID-19 pandemic have relied on large-scale and protracted compliance by the public. A series of studies have recently argued that previous voting patterns are important predictors of such compliance. Our research further investigates such connection by tracking the relationships between parties' vote shares and mobility in six European countries over an extended period of time. We observe that while vote shares are occasionally related to variations in mobility within each country, there is no systematic pattern of decrease or increase in mobility across all six selected countries depending on party family or government membership. Over time, the relationships between mobility and vote shares tend to grow stronger in some but not all countries, again suggesting that there is no clear connection between vote shares for several party families and compliance with social distancing measures.

stat.AP↗

arXiv2021

Monitoring COVID-19-induced gender differences in teleworking rates using Mobile Network Data

The COVID-19 pandemic has created a sudden need for a wider uptake of home-based telework as means of sustaining the production. Generally, teleworking arrangements impacts directly worker's efficiency and motivation. The direction of this impact, however, depends on the balance between positive effects of teleworking (e.g. increased flexibility and autonomy) and its downsides (e.g. blurring boundaries between private and work life). Moreover, these effects of teleworking can be amplified in case of vulnerable groups of workers, such as women. The first step in understanding the implications of teleworking on women is to have timely information on the extent of teleworking by age and gender. In the absence of timely official statistics, in this paper we propose a method for nowcasting the teleworking trends by age and gender for 20 Italian regions using mobile network operators (MNO) data. The method is developed and validated using MNO data together with the Italian quarterly Labour Force Survey. Our results confirm that the MNO data have the potential to be used as a tool for monitoring gender and age differences in teleworking patterns. This tool becomes even more important today as it could support the adequate gender mainstreaming in the ``Next Generation EU'' recovery plan and help to manage related social impacts of COVID-19 through policymaking.

cs.SI↗

arXiv2021

Mobility Functional Areas and COVID-19 Spread

This work introduces a new concept of functional areas called Mobility Functional Areas (MFAs), i.e., the geographic zones highly interconnected according to the analysis of mobile positioning data. The MFAs do not coincide necessarily with administrative borders as they are built observing natural human mobility and, therefore, they can be used to inform, in a bottom-up approach, local transportation, spatial planning, health and economic policies. After presenting the methodology behind the MFAs, this study focuses on the link between the COVID-19 pandemic and the MFAs in Austria. It emerges that the MFAs registered an average number of infections statistically larger than the areas in the rest of the country, suggesting the usefulness of the MFAs in the context of targeted re-escalation policy responses to this health crisis. The MFAs dataset is openly available to other scholars for further analyses.

stat.AP↗

arXiv2021

On the Use of Data from Multiple Mobile Network Operators in Europe to fight COVID-19

The rapid spread of COVID-19 infections on a global level has highlighted the need for accurate, transparent and timely information regarding collective mobility patterns to inform de-escalation strategies as well as to provide forecasting capacity for re-escalation policies aiming at addressing further waves of the virus. Such information can be extracted using aggregate anonymised data from innovative sources such as mobile positioning data. This paper presents lessons learnt and results of a unique Business-to-Government (B2G) initiative between several Mobile Network Operators in Europe and the European Commission. Mobile positioning data have supported policy makers and practitioners with evidence and data-driven knowledge to understand and predict the spread of the disease, the effectiveness of the containment measures, their socio-economic impacts while feeding scenarios at EU scale and in a comparable way across countries. The challenges of this data sharing initiative are not limited to data quality, harmonisation, and comparability across countries, however important they are. Equally essential aspects that need to be addressed from the onset are related to data privacy, security, fundamental rights and commercial sensitivity.

stat.AP↗

arXiv2021

Mobility and Economic Impact of COVID-19 Restrictions in Italy using Mobile Network Operator Data

This work presents the analysis of the impact of restrictions on mobility in Italy, with a focus on the period from 6 November 2020 to 31 January 2021, when a three-tier system based on different levels of risk was adopted and applied at regional level to contrast the second wave of COVID-19. The impact is first evaluated on mobility using Mobile Network Operator anonymised and aggregate data shared in the framework of a Business-to-Government initiative with the European Commission. Mobility data, alongside additional information about electricity consuption, are then used to assess the impacts on an economic level of the three-tier system in different areas of the country.

econ.GN↗

arXiv2021

Territorial differences in the spread of COVID-19 in European regions and US counties

This article explores the territorial differences in the onset and spread of COVID-19 and the excess mortality associated with the pandemic, across the European NUTS3 regions and US counties. Both in Europe and in the US, the pandemic arrived earlier and recorded higher Rt values in urban regions than in intermediate and rural ones. A similar gap is also found in the data on excess mortality. In the weeks during the first phase of the pandemic, urban regions in EU countries experienced excess mortality of up to 68pp more than rural ones. We show that, during the initial days of the pandemic, territorial differences in Rt by the degree of urbanisation can be largely explained by the level of internal, inbound and outbound mobility. The differences in the spread of COVID-19 by rural-urban typology and the role of mobility are less clear during the second wave. This could be linked to the fact that the infection is widespread across territories, to changes in mobility patterns during the summer period as well as to the different containment measures which reverse the causality between mobility and Rt.

econ.GN↗

arXiv2021

Twitter Subjective Well-Being Indicator During COVID-19 Pandemic: A Cross-Country Comparative Study

This study analyzes the impact of the COVID-19 pandemic on the subjective well-being as measured through Twitter data indicators for Japan and Italy. It turns out that, overall, the subjective well-being dropped by 11.7% for Italy and 8.3% for Japan in the first nine months of 2020 compared to the last two months of 2019 and even more compared to the historical mean of the indexes. Through a data science approach we try to identify the possible causes of this drop down by considering several explanatory variables including, climate and air quality data, number of COVID-19 cases and deaths, Facebook Covid and flu symptoms global survey, Google Trends data and coronavirus-related searches, Google mobility data, policy intervention measures, economic variables and their Google Trends proxies, as well as health and stress proxy variables based on big data. We show that a simple static regression model is not able to capture the complexity of well-being and therefore we propose a dynamic elastic net approach to show how different group of factors may impact the well-being in different periods, even over a short time length, and showing further country-specific aspects. Finally, a structural equation modeling analysis tries to address the causal relationships among the COVID-19 factors and subjective well-being showing that, overall, prolonged mobility restrictions,flu and Covid-like symptoms, economic uncertainty, social distancing and news about the pandemic have negative effects on the subjective well-being.

econ.GN↗

arXiv2020

On a Japanese Subjective Well-Being Indicator Based on Twitter data

This study presents for the first time the SWB-J index, a subjective well-being indicator for Japan based on Twitter data. The index is composed by eight dimensions of subjective well-being and is estimated relying on Twitter data by using human supervised sentiment analysis. The index is then compared with the analogous SWB-I index for Italy, in order to verify possible analogies and cultural differences. Further, through structural equation models, a causal assumption is tested to see whether the economic and health conditions of the country influence the well-being latent variable and how this latent dimension affects the SWB-J and SWB-I indicators. It turns out that, as expected, the economic and health welfare is only one aspect of the multidimensional well-being that is captured by the Twitter-based indicator.

stat.AP↗

arXiv2020

Anomaly Detection of Mobility Data with Applications to COVID-19 Situational Awareness

This work introduces a live anomaly detection system for high frequency and high-dimensional data collected at regional scale such as Origin Destination Matrices of mobile positioning data. To take into account different granularity in time and space of the data coming from different sources, the system is designed to be simple, yet robust to the data diversity, with the aim of detecting abrupt increase of mobility towards specific regions as well as sudden drops of movements. The methodology is designed to help policymakers or practitioners, and makes it possible to visualise anomalies as well as estimate the effect of COVID-19 related containment or lifting measures in terms of their impact on human mobility as well as spot potential new outbreaks related to large gatherings.

stat.AP↗

arXiv2020

Forecasting asylum-related migration flows with machine learning and data at scale

The effects of the so-called "refugee crisis" of 2015-16 continue to dominate the political agenda in Europe. Migration flows were sudden and unexpected, leaving governments unprepared and exposing significant shortcomings in the field of migration forecasting. Migration is a complex system typified by episodic variation, underpinned by causal factors that are interacting, highly context dependent and short-lived. Correspondingly, migration monitoring relies on scattered data, while approaches to forecasting focus on specific migration flows and often have inconsistent results that are difficult to generalise at the regional or global levels. Here we show that adaptive machine learning algorithms that integrate official statistics and non-traditional data sources at scale can effectively forecast asylum-related migration flows. We focus on asylum applications lodged in countries of the European Union (EU) by nationals of all countries of origin worldwide; the same approach can be applied in any context provided adequate migration or asylum data are available. We exploit three tiers of data - geolocated events and internet searches in countries of origin, detections of irregular crossings at the EU border, and asylum recognition rates in countries of destination - to effectively forecast individual asylum-migration flows up to four weeks ahead with high accuracy. Uniquely, our approach a) monitors potential drivers of migration in countries of origin to detect changes early onset; b) models individual country-to-country migration flows separately and on moving time windows; c) estimates the effects of individual drivers, including lagged effects; d) provides forecasts of asylum applications up to four weeks ahead; e) assesses how patterns of drivers shift over time to describe the functioning and change of migration systems.

stat.AP↗

arXiv2020

Human mobility and COVID-19 initial dynamics

Mobility data at EU scale can help understand the dynamics of the pandemic and possibly limit the impact of future waves. Still, since a reliable and consistent method to measure the evolution of contagion at international level is missing, a systematic analysis of the relationship between human mobility and virus spread has never been conducted. A notable exceptions are France and Italy, for which data on excess deaths, an indirect indicator which is generally considered to be less affected by national and regional assumptions, are available at department and municipality level, respectively. Using this information together with anonymised and aggregated mobile data, this study shows that mobility alone can explain up to 92% of the initial spread in these two EU countries, while it has a slow decay effect after lockdown measures, meaning that mobility restrictions seem to have effectively contribute to save lives. It also emerges that internal mobility is more important than mobility across provinces and that the typical lagged positive effect of reduced human mobility on reducing excess deaths is around 14-20 days. An analogous analysis relative to Spain, for which an IgG SARS-Cov-2 antibody screening study at province level is used instead of excess deaths statistics, confirms the findings. The same approach adopted in this study can be easily extended to other European countries, as soon as reliable data on the spreading of the virus at a suitable level of granularity will be available. Looking at past data, relative to the initial phase of the outbreak in EU Member States, this study shows in which extent the spreading of the virus and human mobility are connected.

stat.AP↗

arXiv2020

Is Japanese gendered language used on Twitter ? A large scale study

This study analyzes the usage of Japanese gendered language on Twitter. Starting from a collection of 408 million Japanese tweets from 2015 till 2019 and an additional sample of 2355 manually classified Twitter accounts timelines into gender and categories (politicians, musicians, etc). A large scale textual analysis is performed on this corpus to identify and examine sentence-final particles (SFPs) and first-person pronouns appearing in the texts. It turns out that gendered language is in fact used also on Twitter, in about 6% of the tweets, and that the prescriptive classification into "male" and "female" language does not always meet the expectations, with remarkable exceptions. Further, SFPs and pronouns show increasing or decreasing trends, indicating an evolution of the language used on Twitter.

cs.CL↗

arXiv2020

Are official confirmed cases and fatalities counts good enough to study the COVID-19 pandemic dynamics? A critical assessment through the case of Italy

As the COVID-19 outbreak is developing the two most frequently reported statistics seem to be the raw confirmed case and case fatalities counts. Focusing on Italy, one of the hardest hit countries, we look at how these two values could be put in perspective to reflect the dynamics of the virus spread. In particular, we find that merely considering the confirmed case counts would be very misleading. The number of daily tests grows, while the daily fraction of confirmed cases to total tests has a change point. It (depending on region) generally increases with strong fluctuations till (around, depending on region) 15th-22nd March and then decreases linearly after. Combined with the increasing trend of daily performed tests, the raw confirmed case counts are not representative of the situation and are confounded with the sampling effort. This we observe when regressing on time the logged fraction of positive tests and for comparison the logged raw confirmed count. Hence, calibrating model parameters for this virus's dynamics should not be done based only on confirmed case counts (without rescaling by the number of tests), but take also fatalities and hospitalization count under consideration as variables not prone to be distorted by testing efforts. Furthermore, reporting statistics on the national level does not say much about the dynamics of the disease, which are taking place at the regional level. These findings are based on the official data of total death counts up to 15th April 2020 released by ISTAT and up to 10th May 2020 for the number of cases. In this work we do not fit models but we rather investigate whether this task is possible at all. This work also informs about a new tool to collect and harmonize official statistics coming from different sources in the form of a package for the R statistical environment and presents the COVID-19 Data Hub.

stat.AP↗