Resumo

Este artigo analisou as possíveis relações entre os chamados “populismo penal” e “populismo digital”. Para tanto, observamos as relações entre tais fenômenos a partir das postagens no Facebook durante a pandemia de Covid-19 (2020-2021) de políticos brasileiros vinculados à direita e à extrema-direita, e que apresentam altos índices de engajamento, com enfoque nos enquadramentos que conferiram à agenda da segurança pública. Problematizamos se a noção de populismo, seja penal ou digital, é pertinente à caracterização destas narrativas, o que se concretizou para algumas postagens. Contudo, os dados revelam que essa narrativa no Brasil é parcialmente antissistêmica e possui uma característica peculiar: a construção da imagem das polícias como aliadas da classe trabalhadora.

Palavras-Chaves: Populismo penal. Populismo digital. Segurança pública. Análise de discurso. Enquadramentos.

DOI: http://dx.doi.org/10.9771/ccrh.v38i0.67186

Abstract

Visualizing multiple time series presents fundamental tradeoffs between scalability and visual clarity. Time series capture the behavior of many large-scale real-world processes, from stock market trends to urban activities. Users often gain insights by visualizing them as line charts, juxtaposing or superposing multiple time series to compare them and identify trends and patterns. However, existing representations struggle with scalability: when covering long time spans, leading to visual clutter from too many small multiples or overlapping lines. We propose TiVy, a new algorithm that summarizes time series using sequential patterns. It transforms the series into a set of symbolic sequences based on subsequence visual similarity using Dynamic Time Warping (DTW), then constructs a disjoint grouping of similar subsequences based on the frequent sequential patterns. The grouping result, a visual summary of time series, provides uncluttered superposition with fewer small multiples. Unlike common clustering techniques, TiVy extracts similar subsequences (of varying lengths) aligned in time. We also present an interactive time series visualization that renders large-scale time series in real-time. Our experimental evaluation shows that our algorithm (1) extracts clear and accurate patterns when visualizing time series data, (2) achieves a significant speed-up (1000⇥) compared to a straightforward DTW clustering. We also demonstrate the efficiency of our approach to explore hidden structures in massive time series data in two usage scenarios.

Keywords: Time Series Visualization, Sub-sequence Clustering

DOI: https://doi.org/10.1109/TVCG.2025.3633882

Abstract

Time series data are prevalent across various domains and often encompass large datasets containing multiple time-dependent features in each sample. Exploring time-varying data is critical for data science practitioners aiming to understand dynamic behaviors and discover periodic patterns and trends. However, the analysis of such data often requires sophisticated procedures and tools. Information visualization is a communication channel that leverages human perceptual abilities to transform abstract data into visual representations. Visualization techniques have been successfully applied in the context of time series to enhance interpretability by graphically representing the temporal evolution of data. The challenge for information visualization developers lies in integrating a wide range of analytical tools into rich visualization systems that can summarize complex datasets while clearly describing the impacts of the temporal component. Such systems enable data scientists to turn raw data into understandable and potentially useful knowledge. This review examines techniques and approaches designed for handling time series data, guiding users through knowledge discovery processes based on visual analysis. We also provide readers with theoretical insights and design guidelines for considering when developing comprehensive information visualization approaches for time series, with a particular focus on time series with multiple features. As a result, we highlight the challenges and future research directions to address open questions in the visualization of time-dependent data.

Keywords: InfoVis, visual data analysis, user interfaces, interactivity, graphical properties.

DOI: https://doi.org/10.1109/ACCESS.2025.3609404

Abstract

As cities have evolved, so too have crimes, becoming increasingly sophisticated, violent, and intense. This evolution has pushed security models to their breaking point, rendering many traditional strategies obsolete in the face of these new challenges. Consequently, society, especially law enforcement agencies, needs more sophisticated tools to assist them in decision-making. The growing digitization of data over the last decade has enabled the large-scale and highly agile collection of urban data which can be exploited to conduct crime analysis tasks and in particular to identify relevant crime patterns. In this study, we present a computational methodology to investigate the relationship between crime occurrences and the proximity to points of interest (POIs) within a city. In particular, this methodology can perform a segmented analysis, according to socioeconomic patterns of different city regions, using clustering algorithms. Through case studies in the Brazilian cities of Maceió and Arapiraca, we validate the proposed methodology and demonstrate a global correlation between POIs and crime occurrences in both cities. Furthermore, this correlation varies significantly when analyzing street corners segmented by socioeconomic patterns and across both cities. These findings validate the proposed methodology and demonstrate that this approach provides a robust framework for strategic decision-making, enabling law enforcement agencies to allocate resources more effectively and enhance overall public safety.

Keywords: Crime prediction, Urban data, Points of Interest (POIs), Urban crime analysis

DOI: 

Abstract

Feature attribution techniques are crucial for interpreting machine learning models, but practitioners often face difficulties to understand how different methods compare and which one best fits their analytical goals. This difficulty arises from inconsistent results across methods, evaluation metrics that emphasize distinct and sometimes conflicting properties, and subjective preferences that influence how explanation quality is interpreted. In this paper, we introduce Explainalytics, an open-source Python library that transforms this challenging decision-making process into an evidence-based visual analytics workflow. Explainalytics calculates a range of evaluation metrics and presents the results through five coordinated views spanning global to local analysis. Linked filtering, dynamic updates, and brushing allow users to pivot fluidly between global trends and local details, supporting exploratory sense-making rather than rigid pipelines. In a within-subject laboratory study with 10 machine learning practitioners, we compared Explainalytics against a baseline. Explainalytics users experienced significantly lower cognitive workload and higher perceived usability.

Keywords: Explainable AI, Trustworthy explanations, Human-centered explainable AI, Feature attribution

DOI: https://doi.org/10.1016/j.is.2025.102661

Resumo

The connection between urban forests and phenomena such as heat islands, air pollution, property values, and public perceptions of safety has been the subject of extensive research over the years. A fundamental requirement for such studies is the accurate mapping of the spatial distribution of green areas. In this context, this work presents a concise and reproducible framework to map urban forests and generate datasets detailing their location and distribution within metropolitan regions. The proposed methodology relies on freely available imagery from the CBERS-4A satellite and the open-source QGIS software. While auxiliary layers such as city layout and shadow masks are used during the modeling process, their purpose is solely to enhance the accuracy of urban forest classification, not to serve as final outputs. The true merit of this approach lies in its ability to identify urban tree cover patterns with high accuracy, making it a scalable solution for urban green infrastructure studies. The framework is applied to map urban forests in the central area of the city of São Paulo, Brazil.

Palavras-Chaves: Urban forest, urban green space, land cover classification, CBERS-4A, OBIA, Random Forest, dataset.

DOI: https://doi.org/10.1109/SIBGRAPI67909.2025.11223344

Resumo

Urban analytics utilizes extensive datasets with diverse urban information to simulate, predict trends, and uncover complex patterns within cities. While these data enables advanced analysis, it also presents challenges due to its granularity, heterogeneity, and multimodality. To address these challenges, visual analytics tools have been developed to support the exploration of latent representations of fused heterogeneous and multimodal data, discretized at a street-level of detail. However, visualizationassisted tools seldom explore the extent to which fused data can offer deeper insights than examining each data source independently within an integrated visualization framework. In this work, we developed a visualization-assisted framework to analyze whether fused latent data representations are more effective than separate representations in uncovering patterns from dynamic and static urban data. The analysis reveals that combined latent representations produce more structured patterns, while separate ones are useful in particular cases.

DOI: http://www.doi.org/10.1109/SIBGRAPI67909.2025.11223351

Resumo

Criminal incidents have complex socio-economic impacts and reduce the population’s perceived security. Accurate short-term crime-rate forecasting enables more efficient allocation of policing resources and better strategic decisions to mitigate criminal activity. Transformer-based architectures are effective at capturing complex temporal dependencies in time series forecasting; however, model behaviour and the structure of learned representations are strongly influenced by the training loss. In this work, we present a comparative analysis of Transformer and recurrent architectures trained with two different losses, the Mean Squared Error (MSE) and the Soft Dynamic Time Warping (Soft-DTW), with focus on short-term forecasting of vehicle thefts in Sao Paulo. Our goal is to produce embeddings ˜ that are more representative of crime dynamics and thus more useful for downstream tasks such as visualization and pattern analysis. We evaluate Autoformer, ITransformer, and Informer alongside LSTM and GRU baselines, using three performance metrics: MSE, MAE and DTW. Overall, models trained with the DTW-based loss achieved performance similar to, or slightly worse than, those trained with MSE; an important exception is the Autoformer, which showed improved accuracy with SoftDTW at the 14-day horizon. We discuss several factors that likely affected these results: (i) the short forecasting horizons studied, (ii) the formulation of the prediction task (forecasting the entire aggregated series may not be optimal), and (iii) aggregation to daily city-level counts, which discards spatial heterogeneity and may remove salient signal. These findings motivate further experiments (e.g., multi-scale and spatially resolved forecasting) to more comprehensively assess the comparative effectiveness of Soft-DTW and MSE for criminal time series prediction.

Palavras-Chaves: 

DOI: 

Abstract

The Kernel Density Estimation (KDE), also known as heatmap, is one of the most popular techniques to visualize hotspots. However, when it comes to street crimes, the traditional KDE can become inaccurate as it does not consider the road network restrictions, and uses Euclidean distances to measure the degree of interaction between two events. This study proposes the application of a network version of KDE, namely Network Kernel Density Estimation (NKDE) to uncover hotspots of car robberies in São Paulo, Brazil. The NKDE obtains density values only along the street network, using network distances for locating and weighting neighbors. The data was comprised by the 2018 police reports from the São Paulo State Public Security Secretary, totaling 67,637 georeferenced records, and three variations of KDE were applied. The first followed the traditional method, adopting a bandwidth of 500 meters and a resolution of 100 meters per pixel. The second approach employed the NKDE, considering 100m lixels (street segments) and the same bandwidth. As crime occurrences have been shown to be correlated with areas with high levels of activity, the third variation used NKDE weighted by the inverse of an exposure variable, defined in this study as the number of jobs near the crime location. The results of the traditional KDE and NKDE were similar, highlighting the same areas as hotspots. However, in the NKDE, the exact streets showing high density values could be identified. The analysis of the weighted NKDE revealed a distinct scenario: few streets were identified as hotspots, and an area previously not classified as of high density emerged as critical, possibly indicating a mismatch between crime density and local traffic. While NKDE can be used to find the most problematic streets, its weighted version could stablish a priority rule, supporting the strategic allocation of security resources. 

Abstract

The Brazilian Supreme Court serves as the highest judicial authority in Brazil and is responsible for adjudicating constitutional matters presented as extraordinary appeals. These appeals undergo a rigorous screening process guided by established legal principles known as Topics of General Repercussion. Seeking to streamline this procedure, we developed LegalAnalytics to explore the research question: Can machine learning and explainable AI techniques enhance the classification of appeals in legal workflows? LegalAnalytics harnesses advanced natural language processing algorithms and classification models to categorize each appeal according to the most pertinent topics accurately. In addition, it incorporates LIME (Local Interpretable Model-agnostic Explanations) to highlight the key sections of an appeal and compare them with relevant precedents. This approach ensures a transparent justification for every classification. The system is thoughtfully designed with a user-friendly interface tailored for public servants, judges, and lawyers. Extensive testing with dozens of legal experts confirmed the effectiveness of LegalAnalytics, with consistently positive feedback underscoring its significant practical impact.

Keywords:  Visual analytics · Legal document classification · Natural language processing · Explainable AI

DOI: https://doi.org/10.1007/s10506-025-09446-w

Abstract

Maintaining low dropout rates remains a fundamental priority for higher education institutions. Each year, numerous students depart for various reasons, including socioeconomic challenges, academic difficulties, and social issues. For the offices tasked with monitoring enrollment and dropout trends, it is crucial to obtain a comprehensive and timely understanding of these dynamics. Regrettably, existing tools often fall short in providing an effective and straightforward means to explore and identify the key factors contributing to student dropout, thus hindering agile decision-making processes. In response to this challenge, we introduce a novel tool designed to enhance student analysis, facilitate the early detection of potential dropouts, and recommend viable strategies to mitigate attrition in higher education. This tool, named as SDR-Explorer, comprises multiple linked views that empower analysts to (i) visually monitor students’ academic performance over multiple semesters, (ii) interactively examine student features to uncover patterns and clusters, (iii) predict potential dropouts for upcoming periods, and (iv) propose actionable actions over specific student characteristics to reduce dropout rates. Furthermore, the system incorporates a textual assistant that enhances the user experience by assisting in the selection, filtering, summarization, and narrative presentation of proposed changes in natural language. This feature significantly contributes to a more efficient and enjoyable analytical process. Finally, we present two usage scenarios derived from real data collected at a university, alongside a user evaluation designed to assess the usability of our system in terms of accuracy and the time required to complete analytical tasks.

Keywords: Student dropout visualization, LLM-assisted exploration, Visual analytics for education

DOI: https://doi.org/10.1016/j.cag.2025.104375