Bruno Martins
Biographic Data
| ID | 4375421 |
|---|---|
| NAME | Bruno Martins |
| GIVEN NAMES | Bruno |
| FAMILY NAME | Martins |
| SIGNATURE | MARTINS B |
| AFFILIATIONS | Instituto de Engenharia de Sistemas e Computadores Investigação e Desenvolvimento |
| ORCID | 0000-0002-3856-2936 |
| VERIFIED | Yes |
| TOTAL WORKS | 11 |
| TOTAL CITATIONS | 16 |
| WORKS AS AUTHOR | 10 |
| WORKS AS EDITOR | 1 |
| FIRST PUBLICATION YEAR | 2014 |
| LATEST PUBLICATION YEAR | 2025 |
| H-INDEX | 1 |
Child-Friendly Cities
Espaço-mídia-tempo
Editorial: "Em busca de um local: territorializar a crítica e a historiografia das mídias"
Assessing the Prevalence and Predictors of Incivility in Online News Comments Across Six Countries
Drawing on discussions about the manifestation of incivility in online news comments sections, our research operationalizes the concept of incivility and suggests a methodological approach that relies on manual and automated text analysis and regression analysis to assess its prevalence and identify its predictors. Relying on a data analysis of over two million comments on immigration and unemployment retrieved from twelve newspapers websites fro…
The Pluriverse of Human Rights
Deep Learning for Toponym Resolution
Geocoding aims to assign unambiguous locations (i.e., geographic coordinates) to place names (i.e., toponyms) referenced within documents (e.g., within spreadsheet tables or textual paragraphs). This task comes with multiple challenges, such as dealing with referent ambiguity (multiple places with a same name) or reference database completeness. In this work, we propose a geocoding approach based on modeling pairs of toponyms, which returns latit…
Geospatial Data Disaggregation through Self-Trained Encoder–Decoder Convolutional Models
Datasets collecting demographic and socio-economic statistics are widely available. Still, the data are often only released for highly aggregated geospatial areas, which can mask important local hotspots. When conducting spatial analysis, one often needs to disaggregate the source data, transforming the statistics reported for a set of source zones into values for a set of target zones, with a different geometry and a higher spatial resolution. T…
A Novel Deep Learning Approach Using Contextual Embeddings for Toponym Resolution
This article describes a novel approach for toponym resolution with deep neural networks. The proposed approach does not involve matching references in the text against entries in a gazetteer, instead directly predicting geo-spatial coordinates. Multiple inputs are considered in the neural network architecture (e.g., the surrounding words are considered in combination with the toponym to disambiguate), using pre-trained contextual word embeddings…
Developing Geographically Oriented NLP Approaches to Sixteenth–Century Historical Documents
This article introduces an ongoing Digital Humanities project aimed at leveraging the benefits of Natural Language Processing, Corpus Linguistics, Machine Learning, and Spatial Analysis for advancing the computational analysis of vast historical corpora. As a case study, the project concentrates on the Relaciones Geográficas de la Nueva España (1577–1585), one of the key corpora for understanding the early colonial period of Mexico. Using a compu…
Speechmaking and the Selectorate
This article examines the extent to which legislators use legislative debates to engage in localism activities to cater to the interests of their selectorate in nonpreferential electoral systems. We define localism activities as the delivery of tangible and intangible benefits to a geographically confined constituency that is instrumental to legislators’ re-selection. Our primary argument is that legislators whose selectorate operates at the loca…
The 2014 volcanic eruption in Fogo and the reterritorialization process
The population of Fogo Island, in Cape Verde, shows a peculiar relationship with the living territory, given that the eminence of volcanic risk is a reality they face every day. The 1951 and 1995 eruptions were particularly scarring in this insular geography, leaving in several generations of Cape Verdeans, the mark of a creation‐destruction‐restart cycle, as well as an attitude of symbiosis with nature. This article is intended to present and di…
Using machine learning methods for disambiguating place references in textual documents
Speechmaking and the Selectorate
This article examines the extent to which legislators use legislative debates to engage in localism activities to cater to the interests of their selectorate in nonpreferential electoral systems. We define localism activities as the delivery of tangible and intangible benefits to a geographically confined constituency that is instrumental to legislators’ re-selection. Our primary argument is that legislators whose selectorate operates at the loca…
Using machine learning methods for disambiguating place references in textual documents
The 2014 volcanic eruption in Fogo and the reterritorialization process
The population of Fogo Island, in Cape Verde, shows a peculiar relationship with the living territory, given that the eminence of volcanic risk is a reality they face every day. The 1951 and 1995 eruptions were particularly scarring in this insular geography, leaving in several generations of Cape Verdeans, the mark of a creation‐destruction‐restart cycle, as well as an attitude of symbiosis with nature. This article is intended to present and di…
Developing Geographically Oriented NLP Approaches to Sixteenth–Century Historical Documents
This article introduces an ongoing Digital Humanities project aimed at leveraging the benefits of Natural Language Processing, Corpus Linguistics, Machine Learning, and Spatial Analysis for advancing the computational analysis of vast historical corpora. As a case study, the project concentrates on the Relaciones Geográficas de la Nueva España (1577–1585), one of the key corpora for understanding the early colonial period of Mexico. Using a compu…
Speechmaking and the Selectorate
This article examines the extent to which legislators use legislative debates to engage in localism activities to cater to the interests of their selectorate in nonpreferential electoral systems. We define localism activities as the delivery of tangible and intangible benefits to a geographically confined constituency that is instrumental to legislators’ re-selection. Our primary argument is that legislators whose selectorate operates at the loca…
The Pluriverse of Human Rights
Deep Learning for Toponym Resolution
Geocoding aims to assign unambiguous locations (i.e., geographic coordinates) to place names (i.e., toponyms) referenced within documents (e.g., within spreadsheet tables or textual paragraphs). This task comes with multiple challenges, such as dealing with referent ambiguity (multiple places with a same name) or reference database completeness. In this work, we propose a geocoding approach based on modeling pairs of toponyms, which returns latit…
Geospatial Data Disaggregation through Self-Trained Encoder–Decoder Convolutional Models
Datasets collecting demographic and socio-economic statistics are widely available. Still, the data are often only released for highly aggregated geospatial areas, which can mask important local hotspots. When conducting spatial analysis, one often needs to disaggregate the source data, transforming the statistics reported for a set of source zones into values for a set of target zones, with a different geometry and a higher spatial resolution. T…
A Novel Deep Learning Approach Using Contextual Embeddings for Toponym Resolution
This article describes a novel approach for toponym resolution with deep neural networks. The proposed approach does not involve matching references in the text against entries in a gazetteer, instead directly predicting geo-spatial coordinates. Multiple inputs are considered in the neural network architecture (e.g., the surrounding words are considered in combination with the toponym to disambiguate), using pre-trained contextual word embeddings…
Assessing the Prevalence and Predictors of Incivility in Online News Comments Across Six Countries
Drawing on discussions about the manifestation of incivility in online news comments sections, our research operationalizes the concept of incivility and suggests a methodological approach that relies on manual and automated text analysis and regression analysis to assess its prevalence and identify its predictors. Relying on a data analysis of over two million comments on immigration and unemployment retrieved from twelve newspapers websites fro…
Espaço-mídia-tempo
Editorial: "Em busca de um local: territorializar a crítica e a historiografia das mídias"
Child-Friendly Cities
Computer Science (6 works) · Geography (6 works) · Artificial Intelligence (4 works) · Cartography (4 works) · Geographic Information Systems Studies (4 works) · Psychology (4 works) · Archaeology (3 works) · Data Management and Algorithms (3 works) · Geospatial analysis (3 works) · Linguistics (3 works)