arXiv subjects

Francisco Rowe

Publications and source records attributed to Francisco Rowe.

17 recordsLinked to original sources

arXiv2026

Hate speech toward migrants on a citizen reporting platform concentrates in neighborhoods undergoing demographic change

Understanding when migration generates social integration or exclusion is a central challenge for urban communities. Existing research has mostly relied on surveys, administrative data, or aggregate indicators that fail to capture expressions of exclusion at fine spatiotemporal scales. Here, we analyze over 550,000 geolocated reports from SOSAFE (Chile's largest citizen reporting platform) to examine the relationship between migration and hate speech in Santiago. We fine-tune a Spanish hate speech classifier and validate it against human labels. Reports that mention migrants are more likely to contain hate speech than other reports. Hate speech concentrates in areas with recent demographic change (post-2010 arrivals) rather than in established migrant communities. The spatial analysis shows that hate speech hotspots coincide with neighborhoods where recent migrants comprise over a third of the population. Coldspots appear in high-education sectors with minimal recent migration. Reports with hate speech and reports that mention migrants receive more engagement, although their combination is not amplified further. These results show digital bordering on a citizen reporting platform: exclusionary discourse concentrates, and receives more engagement, in neighborhoods undergoing recent demographic change.

cs.SI↗

arXiv2026

One country, multiple portraits: representativeness in GPS-based mobility data is source-specific and spatially dependent

Anonymised GPS-based mobile phone data are increasingly used to estimate population distribution and human mobility, supporting applications across disaster response, public health, urban planning and migration research. Yet whether these data fairly represent the populations they describe, particularly outside high-income countries, remains poorly understood. We quantify coverage bias for 2,478 municipalities in Mexico by comparing population estimates from a single-platform source (Facebook) and a multi-app aggregator (Veraset) against the 2020 Mexican Population Census. We find that the magnitude and spatial distribution of coverage bias differ substantially across sources. Facebook provides higher and more evenly distributed coverage, whereas the multi-app data concentrate users in larger, wealthier and more digitally connected places. Coverage bias is also spatially structured, with neighbouring municipalities showing similar levels of over- or under-coverage. Using explainable machine learning, we show that digital access and material resources are the dominant drivers of bias for the multi-app data, while demographic and population structure dominate for Facebook. Explicitly modelling spatial dependence improves the performance of statistical models for explaining bias and reveals that an appreciable share of spatial variation remains unexplained by observed covariates. These findings show that coverage bias is source-specific and spatially dependent, and provide a foundation for adjustments that improve the representativeness of mobile phone data in unequal, data-scarce settings.

physics.soc-ph↗

arXiv2026

Geospatial foundation-model embeddings improve population estimation unevenly across space and scale

Reliable subnational population estimates are essential for applications, yet remain difficult where censuses are sparse, outdated or spatially coarse. Existing population-mapping workflows rely on hand-built geospatial covariates, such as settlement extent, night-time lights, and environmental conditions, which must be assembled and harmonised across scales and geographies. Geospatial foundation models offer an alternative by learning reusable representations of place from more multifaceted and heterogeneous data sources. Here, we benchmark Population Dynamics Foundation Model (PDFM) embeddings against the harmonised geospatial covariates for subnational population estimation in Brazil, Nigeria and the United States. Under geographically structured validation, PDFM increased predictive fit by a median of 20.1% (IQR: 10.0-33.2%, across country-model comparisons) reduction in unexplained variance, and reduced Kullback-Leibler divergence by 23.2% (9.2-26.2%). However, these gains were uneven. PDFM was most advantageous where the geospatial covariates weakly characterised settlement context, such as larger and less-developed subnational areas. Moreover, PDFM performance was scale-coupled with embeddings providing less flexible transfer across spatial aggregations than geospatial covariates. These findings showed that geospatial foundation-model representations of place can improve population estimation in data poor settings, but their benefits break down predictably under spatial scale mismatch, revealing a fundamental limitation of current geospatial AI.

cs.LG↗

arXiv2025

Dynamic Estimates of Displacement in Disaster Regions: A Policy-driven framework triangulating data

While traditional data systems remain fundamental to humanitarian response, they often lack the real-time responsiveness and spatial precision needed to capture increasingly complex patterns of displacement. Internal displacement reached an unprecedented 83.4 million people by the end of 2024, underscoring the urgent need for innovative, data driven approaches to monitor and understand population movements. This report examines how integrating traditional data sources with emerging digital trace data, such as mobile phone GPS and social media activity, can enhance the accuracy, responsiveness, and granularity of displacement monitoring. Drawing on lessons from recent crises, including the escalation of the war in Ukraine and the 2022 floods in Pakistan, the report presents a structured pilot effort that tests the triangulation of multiple data streams to produce more robust and reliable displacement estimates. Statistical indicators derived from digital trace data are benchmarked against the International Organisation for Migration, Displacement Tracking Matrix datasets, to assess their validity, transparency, and scalability. The findings demonstrate how triangulated data approaches can deliver real-time, high-resolution insights into population movements, improving humanitarian resource allocation and intervention planning. The report includes a scalable framework for crisis monitoring that leverages digital innovation to strengthen humanitarian data systems and support evidence-based decision-making in complex emergencies.

physics.soc-ph↗

arXiv2025

A systematic machine learning approach to measure and assess biases in mobile phone population data

Traditional sources of population data, such as censuses and surveys, are costly, infrequent, and often unavailable in crisis-affected regions. Mobile phone application data offer near real-time, high-resolution insights into population distribution, but their utility is undermined by unequal access to and use of digital technologies, creating biases that threaten representativeness. Despite growing recognition of these issues, there is still no standard framework to measure and explain such biases, limiting the reliability of digital traces for research and policy. We develop and implement a systematic, replicable framework to quantify coverage bias in aggregated mobile phone application data without requiring individual-level demographic attributes. The approach combines a transparent indicator of population coverage with explainable machine learning to identify contextual drivers of spatial bias. Using four datasets for the United Kingdom benchmarked against the 2021 census, we show that mobile phone data consistently achieve higher population coverage than major national surveys, but substantial biases persist across data sources and subnational areas. Coverage bias is strongly associated with demographic, socioeconomic, and geographic features, often in complex nonlinear ways. Contrary to common assumptions, multi-application datasets do not necessarily reduce bias compared to single-app sources. Our findings establish a foundation for bias assessment standards in mobile phone data, offering practical tools for researchers, statistical agencies, and policymakers to harness these datasets responsibly and equitably.

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

Sustained changes to urban mobility after COVID-19 amplified socio-economic inequalities in Latin America

Urban mobility is central to economic activity, social inclusion, and access to essential services. COVID-19 caused disruptions to mobility globally, yet its long-term impacts in less developed countries remain poorly understood. Using over 170 million anonymised mobile phone records from Meta-Facebook users in Argentina, Chile, and Colombia (March 2020 to May 2022), we find sustained changes in mobility across socioeconomic and rural-urban gradients. We reveal that mobility recorded the sharpest declines and remained below pre-pandemic levels in most high-density and low socio-economic deprivation areas, while low-density and more deprived communities returned to baseline. These differences reflect the scale of the initial mobility shock rather than subsequent recovery rates. Net mobility to urban cores remained consistently below pre-pandemic levels, suggesting a shift in their functional role. By revealing how COVID-19 reinforced mobility-related inequalities, we contribute novel evidence for planners and policymakers seeking to build more inclusive and resilient mobility systems.

physics.soc-ph↗

arXiv2025

Producing population-level estimates of internal displacement in Ukraine using GPS mobile phone data

Nearly 110 million people are forcibly displaced people worldwide. However, estimating the scale and patterns of internally displaced persons in real time, and developing appropriate policy responses, remain hindered by traditional data streams. They are infrequently updated, costly and slow. Mobile phone location data can overcome these limitations, but only represent a population segment. Drawing on an anonymised large-scale, high-frequency dataset of locations from 25 million mobile devices, we propose an approach to leverage mobile phone data and produce population-level estimates of internal displacement. We use this approach to quantify the extent, pace and geographic patterns of internal displacement in Ukraine during the early stages of the Russian invasion in 2022. Our results produce reliable population-level estimates, enabling real-time monitoring of internal displacement at detailed spatio-temporal resolutions. Accurate estimations are crucial to support timely and effective humanitarian and disaster management responses, prioritising resources where they are most needed.

physics.soc-ph↗

arXiv2024

Unveiling the influence of behavioural, built environment and socio-economic features on the spatial and temporal variability of bus use using explainable machine learning

Understanding the variability of people's travel patterns is key to transport planning and policy-making. However, to what extent daily transit use displays geographic and temporal variabilities, and what are the contributing factors have not been fully addressed. Drawing on smart card data in Beijing, China, this study seeks to address these deficits by adopting new indices to capture the spatial and temporal variability of bus use during peak hours and investigate their associations with relevant contextual features. Using explainable machine learning, our findings reveal non-linear interaction between spatial and temporal variability and trip frequency. Furthermore, greater distance to the urban centres (>10 kilometres) is associated with increased spatial variability of bus use, while greater separation of trip origins and destinations from the subcentres reduces both spatial and temporal variability. Higher availability of bus routes is linked to higher spatial variability but lower temporal variability. Meanwhile, both lower and higher road density is associated with higher spatial variability of bus use especially in morning times. These findings indicate that different built environment features moderate the flexibility of travel time and locations. Implications are derived to inform more responsive and reliable operation and planning of transit systems.

cs.CY↗

arXiv2024

Exposing Hate -- Understanding Anti-Immigration Sentiment Spreading on Twitter

Immigration is one of the most salient topics in public debate. Social media heavily influences opinions on immigration, often sparking polarized debates and offline tensions. Studying 220,870 immigration-related tweets in the UK, we assessed the extent of polarization, key content creators and disseminators, and the speed of content dissemination. We identify a high degree of online polarization between pro and anti-immigration communities. We found that the anti-migration community is small but denser and more active than the pro-immigration community with the top 1% of users responsible for over 23% of anti-immigration tweets and 21% of retweets. We also discovered that anti-immigration content spreads also 1.66 times faster than pro-immigration messages and bots have minimal impact on content dissemination. Our findings suggest that identifying and tracking highly active users could curb anti-immigration sentiment, potentially easing social polarization and shaping broader societal attitudes toward migration.

cs.SI↗

arXiv2023

Reduced mobility? Urban exodus? Medium-term impacts of the COVID-19 pandemic on internal population movements in Latin American countries

The COVID-19 pandemic has impacted the national systems of population movement around the world. Existing work has focused on countries of the Global North and restricted to the immediate effects of COVID-19 data during 2020. Data have represented a major limitation to monitor change in mobility patterns in countries in the Global South. Drawing on aggregate anonymised mobile phone location data from Meta-Facebook users, we aim to analyse the extent and persistence of changes in the levels (or intensity) and spatial patterns of internal population movement across the rural-urban continuum in Argentina, Chile and Mexico over a 26-month period from March 2020 to May 2022. We reveal an overall systematic decline in the level of short- and long-distance movement during the enactment of nonpharmaceutical interventions in 2020, with the largest reductions occurred in the most dense areas. We also show that these levels bounced back closer to pre-pandemic levels in 2022 following the relaxation of COVID-19 stringency measures. However, the intensity of these movements has remained below pre-pandemic levels in many areas in 2022. Additionally our findings lend some support to the idea of an urban exodus. They reveal a continuing negative net balances of short-distance movements in the most dense areas of capital cities in Argentina and Mexico, reflecting a pattern of suburbanisation. Chile displays limited changes in the net balance of short-distance movements but reports a net loss of long-distance movements. These losses were, however, temporary, moving to neutral and positive balances in 2021 and 2022.

physics.soc-ph↗

arXiv2022

Urban Exodus? Understanding Human Mobility in Britain During the COVID-19 Pandemic Using Facebook Data

Existing empirical work has focused on assessing the effectiveness of non-pharmaceutical interventions on human mobility to contain the spread of COVID-19. Less is known about the ways in which the COVID-19 pandemic has reshaped the spatial patterns of population movement within countries. Anecdotal evidence of an urban exodus from large cities to rural areas emerged during early phases of the pandemic across western societies. Yet, these claims have not been empirically assessed. Traditional data sources, such as censuses offer coarse temporal frequency to analyse population movement over short-time intervals. Drawing on a data set of 21 million observations from Facebook users, we aim to analyse the extent and evolution of changes in the spatial patterns of population movement across the rural-urban continuum in Britain over an 18-month period from March, 2020 to August, 2021. Our findings show an overall and sustained decline in population movement during periods of high stringency measures, with the most densely populated areas reporting the largest reductions. During these periods, we also find evidence of higher-than-average mobility from highly dense population areas to low densely populated areas, lending some support to claims of large-scale population movements from large cities. Yet, we show that these trends were temporary. Overall mobility levels trended back to pre-coronavirus levels after the easing of non-pharmaceutical interventions. Following these interventions, we also found a reduction in movement to low density areas and a rise in mobility to high density agglomerations. Overall, these findings reveal that while COVID-19 generated shock waves leading to temporary changes in the patterns of population movement in Britain, the resulting vibrations have not significantly reshaped the prevalent structures in the national pattern of population movement.

physics.soc-ph↗

arXiv2022

Assessing Machine Learning Algorithms for Near-Real Time Bus Ridership Prediction During Extreme Weather

Given an increasingly volatile climate, the relationship between weather and transit ridership has drawn increasing interest. However, challenges stemming from spatio-temporal dependency and non-stationarity have not been fully addressed in modelling and predicting transit ridership under the influence of weather conditions especially with the traditional statistical approaches. Drawing on three-month smart card data in Brisbane, Australia, this research adopts and assesses a suite of machine-learning algorithms, i.e., random forest, eXtreme Gradient Boosting (XGBoost) and Tweedie XGBoost, to model and predict near real-time bus ridership in relation to sudden change of weather conditions. The study confirms that there indeed exists a significant level of spatio-temporal variability of weather-ridership relationship, which produces equally dynamic patterns of prediction errors. Further comparison of model performance suggests that Tweedie XGBoost outperforms the other two machine-learning algorithms in generating overall more accurate prediction outcomes in space and time. Future research may advance the current study by drawing on larger data sets and applying more advanced machine and deep-learning approaches to provide more enhanced evidence for real-time operation of transit systems.

stat.AP↗

arXiv2022

Feel Old Yet? Updating Mode of Transportation Distributions from Travel Surveys using Data Fusion with Mobile Phone Data

Up-to-date information on different modes of travel to monitor transport traffic and evaluate rapid urban transport planning interventions is often lacking. Transport systems typically rely on traditional data sources providing outdated mode-of-travel data due to their data latency, infrequent data collection and high cost. To address this issue, we propose a method that leverages mobile phone data as a cost-effective and rich source of geospatial information to capture current human mobility patterns at unprecedented spatiotemporal resolution. Our approach employs mobile phone application usage traces to infer modes of transportation that are challenging to identify (bikes and ride-hailing/taxi services) based on mobile phone location data. Using data fusion and matrix factorization techniques, we integrate official data sources (household surveys and census data) with mobile phone application usage data. This integration enables us to reconstruct the official data and create an updated dataset that incorporates insights from digital footprint data from application usage. We illustrate our method using a case study focused on Santiago, Chile successfully inferring four modes of transportation: mass-transit, motorised, active, and taxi. Our analysis revealed significant changes in transportation patterns between 2012 and 2020. We quantify a reduction in mass-transit usage across municipalities in Santiago, except where metro/rail lines have been more recently introduced, highlighting added resilience to the public transport network of these infrastructure enhancements. Additionally, we evidence an overall increase in motorised transport throughout Santiago, revealing persistent challenges in promoting urban sustainable transportation. We validate our findings comparing our updated estimates with official smart card transaction data.

cs.CY↗

arXiv2022

Understanding the Trajectories of Population Decline Across Rural and Urban Europe: A Sequence Analysis

Population decline is projected to become widespread in Europe, with the continental population set to reverse its longstanding trajectory of growth within the next five years. This represents unfamiliar demographic territory. Despite this, literature on decline remains sparse and our understanding porous. Particular epistemological deficiencies stem from a lack of both cross-national and temporal analyses of population decline. This study seeks to address these gapsthrough the novel application of sequence and cluster analysis techniques to examine variations in population decline trajectories since 2000 in 696 sub-national areas across 33 European territories. The methodology allows for a holistic understanding of decline trajectories capturing differences in the ordering, timing, magnitude and spatial structure of population decline. We identify a typology of population decline distinguishing seven distinct pathways to depopulation and chart their geographies. Results revealed differentiated pathways of depopulation in continental sub-regions, with consistent and rapid declines in the east, persistent but moderate declines in central Europe, accelerating declines in the south and decelerating population declines in the west. Results also revealed differentiated patterns of depopulation across the rural-urban continuum, with urban and populous areas experiencing deceleration in population decline, while population decline accelerates or stabilises in rural areas. Small and mid-sized areas displayed heterogeneous depopulation trajectories, highlighting the importance of local contextual factors in influencing trajectories of population decline.

q-bio.PE↗

arXiv2021

A city of cities: Measuring how 15-minutes urban accessibility shapes human mobility in Barcelona

As cities expand, human mobility has become a central focus of urban planning and policy making to make cities more inclusive and sustainable. Initiatives such as the "15-minutes city" have been put in place to shift the attention from monocentric city configurations to polycentric structures, increasing the availability and diversity of local urban amenities. Ultimately they expect to increase local walkability and increase mobility within residential areas. While we know how urban amenities influence human mobility at the city level, little is known about spatial variations in this relationship. Here, we use mobile phone, census, and volunteered geographical data to measure geographic variations in the relationship between origin-destination flows and local urban accessibility in Barcelona. Using a Negative Binomial Geographically Weighted Regression model, we show that, globally, people tend to visit neighborhoods with better access to education and retail. Locally, these and other features change in sign and magnitude through the different neighborhoods of the city in ways that are not explained by administrative boundaries, and that provide deeper insights regarding urban characteristics such as rental prices. In conclusion, our work suggests that the qualities of a 15-minutes city can be measured at scale, delivering actionable insights on the polycentric structure of cities, and how people use and access this structure.

cs.SI↗

arXiv2019

Impact of internal migration on population redistribution in Europe: Urbanisation, counterurbanisation or spatial equilibrium?

The classical foundations of migration research date from the 1880s with Ravenstein's Laws of migration, which represent the first comparative analyses of internal migration. While his observations remain largely valid, the ensuing century has seen considerable progress in data collection practices and methods of analysis, which in turn has permitted theoretical advances in understanding the role of migration in population redistribution. Coupling the extensive range of migration data now available with these recent theoretical and methodological advances, we endeavour to advance beyond Ravenstein's understanding by examining the direction of population redistribution and comparing the impact of internal migration on patterns of human settlement in 27 European countries. Results show that the overall redistributive impact of internal migration is low in most European countries but the mechanisms differ across the continent. In Southern and Eastern Europe migration effectiveness is above average but is offset by low migration intensities, whereas in Northern and Western Europe high intensities are absorbed in reciprocal flows resulting in low migration effectiveness. About half the European countries are experiencing a process of concentration toward urbanised regions, particularly in Northern, Central and Eastern Europe, whereas countries in the West and South are undergoing a process of population deconcentration. These results suggest that population deconcentration is now more common than it was in the 1990s when counterurbanisation was limited to Western Europe. The results show that 130 years on, Ravenstein's law of migration streams and counter-streams remains a central facet of migration dynamics, while underlining the importance of simple yet robust indices for the spatial analysis of migration.

stat.AP↗