Thiago Henrique Silva
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Thiago Henrique Silva has a total of 137 co-authors. Here are the top co-authors by number of shared publications:
- Myriam Regattieri Delgado
UTFPR
15 shared publications Antonio A. F. Loureiro
Federal University of Minas Gerais, Belo Horizonte, Brazil
10 shared publicationsJussara M. Almeida
10 shared publications- Pedro Olmo Stancioli Vaz de Melo
Universidade Federal de Minas Gerais, Belo Horizonte, Brazil
10 shared publications - Anelise Munaretto
UTFPR
9 shared publications - Daniel Silver
University of Toronto
9 shared publications
Latest Publications
- Open Access
Grandes Modelos de Linguagem Multimodais (MLLMs): Da Teoria à Prática
Multimodal Large Language Models (MLLMs) combine the natural language understanding and generation capabilities of LLMs with perception skills in modalities such as image and audio, representing a key advancement in contemporary AI. This chapter presents the main fundamentals of MLLMs and emblematic models. Practical techniques for preprocessing, prompt engineering, and building multimodal pipelines with LangChain and LangGraph are also explored. For further practical study, supplementary material is publicly available online: https://github.com/neemiasbsilva/MLLMs-Teoria-e-Pratica. Finally, the chapter discusses the challenges and highlights promising trends.
Open AccessGrandes Modelos de Linguagem Multimodais (MLLMs): Da Teoria à Prática
Multimodal Large Language Models (MLLMs) combine the natural language understanding and generation capabilities of LLMs with perception skills in modalities such as image and audio, representing a key advancement in contemporary AI. This chapter presents the main fundamentals of MLLMs and emblematic models. Practical techniques for preprocessing, prompt engineering, and building multimodal pipelines with LangChain and LangGraph are also explored. For further practical study, supplementary material is publicly available online: https://github.com/neemiasbsilva/MLLMs-Teoria-e-Pratica. Finally, the chapter discusses the challenges and highlights promising trends.
- Open Access
- 9 January 2026
- Published by Sociedade Brasileira de Computação in Journal of Internet Services and Applications
- Vol. 17 (1) , 283-294
Failure Profile Characterization in Heavy-Duty Trucks Using Fuzzy Clustering of Telemetry and Repair Data
Among transportation companies, the most expensive operational costs are due to the maintenance of truck fleets. Data-driven approaches that leverage telemetry and repair data can be effective in addressing such problems. Telemetry data is collected from sensors that monitor truck operational conditions, while repair data is recorded during both scheduled and emergency maintenance. This work characterizes the profiles of Euro 6 heavy-duty trucks using fuzzy clustering to identify vehicles with component failure, specifically within the powertrain system (engine/transmission assembly). Feature selection is based on correlation analysis and extracted from the time series of sensors. Three methods are used to characterize failure profiles: (i) a baseline strategy using averaged feature vectors of failed and non-failed trucks; (ii) Fuzzy C-Means (FCM); and (iii) Fuzzy Self-Organizing Maps (FSOM). These profiles are then used to compute failure risk scores for each truck, based on the similarity to failed and healthy truck references. Our contribution includes a detailed evaluation of FCM and FSOM parameters and their impact on failure results, as well as the identification of usage-related features as stronger predictors of failure than component-specific variables. Results show that the clustering-based strategy can significantly improve failure identification when compared to the baseline. This finding demonstrates the potential to support targeted preventive maintenance with reduced false positives.
- 9 January 2026
- Published by Sociedade Brasileira de Computação in Journal of Internet Services and Applications
- Vol. 17 (1) , 283-294
Open AccessFailure Profile Characterization in Heavy-Duty Trucks Using Fuzzy Clustering of Telemetry and Repair Data
Among transportation companies, the most expensive operational costs are due to the maintenance of truck fleets. Data-driven approaches that leverage telemetry and repair data can be effective in addressing such problems. Telemetry data is collected from sensors that monitor truck operational conditions, while repair data is recorded during both scheduled and emergency maintenance. This work characterizes the profiles of Euro 6 heavy-duty trucks using fuzzy clustering to identify vehicles with component failure, specifically within the powertrain system (engine/transmission assembly). Feature selection is based on correlation analysis and extracted from the time series of sensors. Three methods are used to characterize failure profiles: (i) a baseline strategy using averaged feature vectors of failed and non-failed trucks; (ii) Fuzzy C-Means (FCM); and (iii) Fuzzy Self-Organizing Maps (FSOM). These profiles are then used to compute failure risk scores for each truck, based on the similarity to failed and healthy truck references. Our contribution includes a detailed evaluation of FCM and FSOM parameters and their impact on failure results, as well as the identification of usage-related features as stronger predictors of failure than component-specific variables. Results show that the clustering-based strategy can significantly improve failure identification when compared to the baseline. This finding demonstrates the potential to support targeted preventive maintenance with reduced false positives.
- 23 December 2025
- Published by Springer Nature
- p. 450-456
CityHood: An Explainable Travel Recommender System for Cities and Neighborhoods
- 23 December 2025
- Published by Springer Nature
- p. 450-456
CityHood: An Explainable Travel Recommender System for Cities and Neighborhoods
- Open Access
A Relational Model of Neighborhood Mobility: The Role of Amenities and Cultural Alignment
Why are some neighborhoods strongly connected while others remain isolated? Although standard explanations focus on demographics, economics, and geography, movement across the city may also depend on cultural styles and amenity mix. This study proposes a relational, cross-national model in which local culture and amenity mix alignment creates a "soft infrastructure" of urban mobility, i.e., symbolic cues and functional features that shape expectations about the character of places. Using ~650 million Google Places reviews to measure co-visitation between U.S. ZIP codes and ~30 million Canadian change-of-address to track residential mobility, results show that neighborhoods with similar cultural styles and amenities are significantly more connected. These effects persist even after controlling for race, income, education, politics, housing costs, and distance. Urban cohesion and segregation depend not only on who lives where or how far apart neighborhoods are, but on the shared cultural and material ecologies that structure movement across the city.
Open AccessA Relational Model of Neighborhood Mobility: The Role of Amenities and Cultural Alignment
Why are some neighborhoods strongly connected while others remain isolated? Although standard explanations focus on demographics, economics, and geography, movement across the city may also depend on cultural styles and amenity mix. This study proposes a relational, cross-national model in which local culture and amenity mix alignment creates a "soft infrastructure" of urban mobility, i.e., symbolic cues and functional features that shape expectations about the character of places. Using ~650 million Google Places reviews to measure co-visitation between U.S. ZIP codes and ~30 million Canadian change-of-address to track residential mobility, results show that neighborhoods with similar cultural styles and amenities are significantly more connected. These effects persist even after controlling for race, income, education, politics, housing costs, and distance. Urban cohesion and segregation depend not only on who lives where or how far apart neighborhoods are, but on the shared cultural and material ecologies that structure movement across the city.
- Open Access
- 10 November 2025
- Published by Sociedade Brasileira de Computação
- p. 482-490
Where Next? A Behavioral and Explainable Framework for City and Neighborhood Recommendation
Understanding why individuals choose to visit particular cities and specific neighborhoods within them is essential for advancing both urban mobility research and personalized tourism technologies. This paper proposes a novel multi-level (city and neighborhood levels), explainable recommendation framework that models user interest based on area similarities across geographic, demographic, cultural, and venue-category dimensions. Our approach predicts user interest through a behaviorally informed, interpretable machine learning model. Using large-scale review data from Google Places, enriched with U.S. Census, political, and cultural indicators, we analyze mobility through the lens of high-interest and lowinterest divisions and two behavioral archetypes: returners (who repeatedly visit familiar areas) and explorers (who seek out new destinations). Results show that explorers are more interested in geographically clustered cities, suggesting a search for new experiences in nearby locations. In contrast, returners attach to areas that align with their past experiences (e.g., venue categories). Beyond good predictive performance, our system provides natural-language explanations for each recommendation, offering actionable insights into user behavior. A demonstration system illustrates how our approach enables transparent, behavior-informed travel recommendations. This work bridges gaps in urban AI by integrating spatial granularity, behavioral segmentation, and explainability.
- 10 November 2025
- Published by Sociedade Brasileira de Computação
- p. 482-490
Open AccessWhere Next? A Behavioral and Explainable Framework for City and Neighborhood Recommendation
Understanding why individuals choose to visit particular cities and specific neighborhoods within them is essential for advancing both urban mobility research and personalized tourism technologies. This paper proposes a novel multi-level (city and neighborhood levels), explainable recommendation framework that models user interest based on area similarities across geographic, demographic, cultural, and venue-category dimensions. Our approach predicts user interest through a behaviorally informed, interpretable machine learning model. Using large-scale review data from Google Places, enriched with U.S. Census, political, and cultural indicators, we analyze mobility through the lens of high-interest and lowinterest divisions and two behavioral archetypes: returners (who repeatedly visit familiar areas) and explorers (who seek out new destinations). Results show that explorers are more interested in geographically clustered cities, suggesting a search for new experiences in nearby locations. In contrast, returners attach to areas that align with their past experiences (e.g., venue categories). Beyond good predictive performance, our system provides natural-language explanations for each recommendation, offering actionable insights into user behavior. A demonstration system illustrates how our approach enables transparent, behavior-informed travel recommendations. This work bridges gaps in urban AI by integrating spatial granularity, behavioral segmentation, and explainability.
- Open Access
- 29 September 2025
- Published by Sociedade Brasileira de Computação
- p. 760-766
How Culture Shapes Customers: A Cross-Continent Analysis of Apps Reviews Using NLP Techniques
Understanding customers’ feedback is essential for businesses to improve products and adapt to different markets. This study analyzes 100,000 app reviews from Uber, Instagram, and WhatsApp across six countries (Brazil, U.S., Australia, India, U.K., and South Africa) to assess whether user concerns are global or culturally influenced. Using BERTopic for topic modeling, zero-shot classification for topic assignment, and Aspect-Based Sentiment Analysis, we identify twelve key topics in reviews. While some topics are shared globally, others are country-specific. For example, Uber’s reliability was a major concern in South Africa and Australia, while Brazilian users discussed WhatsApp voice messages more frequently. These findings help businesses detect market-specific trends, benchmark competitors, and address regional needs strategically.
- 29 September 2025
- Published by Sociedade Brasileira de Computação
- p. 760-766
Open AccessHow Culture Shapes Customers: A Cross-Continent Analysis of Apps Reviews Using NLP Techniques
Understanding customers’ feedback is essential for businesses to improve products and adapt to different markets. This study analyzes 100,000 app reviews from Uber, Instagram, and WhatsApp across six countries (Brazil, U.S., Australia, India, U.K., and South Africa) to assess whether user concerns are global or culturally influenced. Using BERTopic for topic modeling, zero-shot classification for topic assignment, and Aspect-Based Sentiment Analysis, we identify twelve key topics in reviews. While some topics are shared globally, others are country-specific. For example, Uber’s reliability was a major concern in South Africa and Australia, while Brazilian users discussed WhatsApp voice messages more frequently. These findings help businesses detect market-specific trends, benchmark competitors, and address regional needs strategically.
- Open Access
CityHood: An Explainable Travel Recommender System for Cities and Neighborhoods
We present CityHood, an interactive and explainable recommendation system that suggests cities and neighborhoods based on users' areas of interest. The system models user interests leveraging large-scale Google Places reviews enriched with geographic, socio-demographic, political, and cultural indicators. It provides personalized recommendations at city (Core-Based Statistical Areas - CBSAs) and neighborhood (ZIP code) levels, supported by an explainable technique (LIME) and natural-language explanations. Users can explore recommendations based on their stated preferences and inspect the reasoning behind each suggestion through a visual interface. The demo illustrates how spatial similarity, cultural alignment, and interest understanding can be used to make travel recommendations transparent and engaging. This work bridges gaps in location-based recommendation by combining a kind of interest modeling, multi-scale analysis, and explainability in a user-facing system.
Open AccessCityHood: An Explainable Travel Recommender System for Cities and Neighborhoods
We present CityHood, an interactive and explainable recommendation system that suggests cities and neighborhoods based on users' areas of interest. The system models user interests leveraging large-scale Google Places reviews enriched with geographic, socio-demographic, political, and cultural indicators. It provides personalized recommendations at city (Core-Based Statistical Areas - CBSAs) and neighborhood (ZIP code) levels, supported by an explainable technique (LIME) and natural-language explanations. Users can explore recommendations based on their stated preferences and inspect the reasoning behind each suggestion through a visual interface. The demo illustrates how spatial similarity, cultural alignment, and interest understanding can be used to make travel recommendations transparent and engaging. This work bridges gaps in location-based recommendation by combining a kind of interest modeling, multi-scale analysis, and explainability in a user-facing system.
- Open Access
Interest Networks (iNETs) for Cities: Cross-Platform Insights and Urban Behavior Explanations
Location-Based Social Networks (LBSNs) provide a rich foundation for modeling urban behavior through iNETs (Interest Networks), which capture how user interests are distributed throughout urban spaces. This study compares iNETs across platforms (Google Places and Foursquare) and spatial granularities, showing that coarser levels reveal more consistent cross-platform patterns, while finer granularities expose subtle, platform-specific behaviors. Our analysis finds that, in general, user interest is primarily shaped by geographic proximity and venue similarity, while socioeconomic and political contexts play a lesser role. Building on these insights, we develop a multi-level, explainable recommendation system that predicts high-interest urban regions for different user types. The model adapts to behavior profiles -- such as explorers, who are driven by proximity, and returners, who prefer familiar venues -- and provides natural-language explanations using explainable AI (XAI) techniques. To support our approach, we introduce h3-cities, a tool for multi-scale spatial analysis, and release a public demo for interactively exploring personalized urban recommendations. Our findings contribute to urban mobility research by providing scalable, context-aware, and interpretable recommendation systems.
Open AccessInterest Networks (iNETs) for Cities: Cross-Platform Insights and Urban Behavior Explanations
Location-Based Social Networks (LBSNs) provide a rich foundation for modeling urban behavior through iNETs (Interest Networks), which capture how user interests are distributed throughout urban spaces. This study compares iNETs across platforms (Google Places and Foursquare) and spatial granularities, showing that coarser levels reveal more consistent cross-platform patterns, while finer granularities expose subtle, platform-specific behaviors. Our analysis finds that, in general, user interest is primarily shaped by geographic proximity and venue similarity, while socioeconomic and political contexts play a lesser role. Building on these insights, we develop a multi-level, explainable recommendation system that predicts high-interest urban regions for different user types. The model adapts to behavior profiles -- such as explorers, who are driven by proximity, and returners, who prefer familiar venues -- and provides natural-language explanations using explainable AI (XAI) techniques. To support our approach, we introduce h3-cities, a tool for multi-scale spatial analysis, and release a public demo for interactively exploring personalized urban recommendations. Our findings contribute to urban mobility research by providing scalable, context-aware, and interpretable recommendation systems.
- Open Access
- 19 May 2025
- Published by Sociedade Brasileira de Computação
- p. 182-191
Urban Perception Extraction from Texts Shared on Social Media: Framework and Applications
This thesis presents an automatic, generic framework for extracting urban perceptions from Location-Based Social Network (LBSN) data. The framework is organized into five key layers: Data Collection, Preprocessing and Embeddings, Model Training, Knowledge Extraction, and Applications. By leveraging deep learning techniques, including advanced sentence embedding methods, the framework captures both lexical and semantic nuances in textual data, thereby efficiently extracting user perceptions of urban environments. This approach eliminates the need for labor-intensive field surveys and manual data extraction, allowing scalable real-time analysis. We validated the framework by applying it to selected urban areas in Chicago, New York City, and London, demonstrating its effectiveness in uncovering valuable insights about urban perceptions. Furthermore, a comparative evaluation using a public dataset derived from volunteers’ perceptions in a controlled experiment revealed a high level of agreement between the two sets of results. As a proof-of-concept, we introduce Real-Estate Urban Perceptions (REAL-UP), an innovative tool designed to enhance the real estate marketplace. REAL-UP provides interactive 2D maps that integrate traditional real-estate data (e.g., rent prices and property types) with enriched information on neighborhood emotions, sentiments, and brief narrative reviews generated by a Large Language Model (LLM) based on LBSN messages.
- 19 May 2025
- Published by Sociedade Brasileira de Computação
- p. 182-191
Open AccessUrban Perception Extraction from Texts Shared on Social Media: Framework and Applications
This thesis presents an automatic, generic framework for extracting urban perceptions from Location-Based Social Network (LBSN) data. The framework is organized into five key layers: Data Collection, Preprocessing and Embeddings, Model Training, Knowledge Extraction, and Applications. By leveraging deep learning techniques, including advanced sentence embedding methods, the framework captures both lexical and semantic nuances in textual data, thereby efficiently extracting user perceptions of urban environments. This approach eliminates the need for labor-intensive field surveys and manual data extraction, allowing scalable real-time analysis. We validated the framework by applying it to selected urban areas in Chicago, New York City, and London, demonstrating its effectiveness in uncovering valuable insights about urban perceptions. Furthermore, a comparative evaluation using a public dataset derived from volunteers’ perceptions in a controlled experiment revealed a high level of agreement between the two sets of results. As a proof-of-concept, we introduce Real-Estate Urban Perceptions (REAL-UP), an innovative tool designed to enhance the real estate marketplace. REAL-UP provides interactive 2D maps that integrate traditional real-estate data (e.g., rent prices and property types) with enriched information on neighborhood emotions, sentiments, and brief narrative reviews generated by a Large Language Model (LLM) based on LBSN messages.