Catarina Marques
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
Catarina Marques has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- António Fonseca
Instituto Universitário de Lisboa (ISCTE-IUL), ISTAR
5 shared publications - Cláudia Silva
ITI-LARSyS and IST
5 shared publications - Fernando Batista
Instituto Universitário de Lisboa (ISCTE-IUL)
5 shared publications - Paula Carvalho
INESC-ID
5 shared publications - Ricardo Ribeiro
INESC-ID Lisboa, Lisboa, Portugal
5 shared publications - Rita Guerra
Centro de Investigação e Intervenção Social (CIS‐ISCTE) ISCTE ‐ Instituto Universitário de Lisboa Lisbon Portugal
5 shared publications
Latest Publications
- 13 February 2025
- Published by Springer Nature
- p. 94-105
Counter Hate Speech Detection in Youtube Conversations
- 13 February 2025
- Published by Springer Nature
- p. 94-105
Counter Hate Speech Detection in Youtube Conversations
- 13 February 2025
- Published by Springer Nature
- p. 70-81
Unveiling Patterns of Hate Speech in the Portuguese Sphere: A Social Network Analysis Approach
- 13 February 2025
- Published by Springer Nature
- p. 70-81
Unveiling Patterns of Hate Speech in the Portuguese Sphere: A Social Network Analysis Approach
- 16 November 2024
- Published by Springer Nature
- p. 241-253
Bypassing the Nuances of Portuguese Covert Hate Speech Through Contextual Analysis
- 16 November 2024
- Published by Springer Nature
- p. 241-253
Bypassing the Nuances of Portuguese Covert Hate Speech Through Contextual Analysis
- Open Access
- 9 October 2024
- Published by Springer Nature in Social Network Analysis and Mining
- Vol. 14 (1) , 1-25
A comprehensive review on automatic hate speech detection in the age of the transformer
The rapid proliferation of hate speech on social media poses significant challenges to maintaining a safe and inclusive digital environment. This paper presents a comprehensive review of automatic hate speech detection methods, with a particular focus on the evolution of approaches from traditional machine learning and deep learning models to the more advanced Transformer-based architectures. We systematically analyze over 100 studies, comparing the effectiveness, computational requirements, and applicability of various techniques, including Support Vector Machines, Long Short-Term Memory networks, Convolutional Neural Networks, and Transformer models like BERT and its multilingual variants. The review also explores the datasets, languages, and sources used for hate speech detection, noting the predominance of English-focused research while highlighting emerging efforts in low-resource languages and cross-lingual detection using multilingual Transformers. Additionally, we discuss the role of generative and multi-task learning models as promising avenues for future development. While Transformer-based models consistently achieve state-of-the-art performance, this review underscores the trade-offs between performance and computational cost, emphasizing the need for context-specific solutions. Key challenges such as algorithmic bias, data scarcity, and the need for more standardized benchmarks are also identified. This review provides crucial insights for advancing the field of hate speech detection and shaping future research directions.
- 9 October 2024
- Published by Springer Nature in Social Network Analysis and Mining
- Vol. 14 (1) , 1-25
Open AccessA comprehensive review on automatic hate speech detection in the age of the transformer
The rapid proliferation of hate speech on social media poses significant challenges to maintaining a safe and inclusive digital environment. This paper presents a comprehensive review of automatic hate speech detection methods, with a particular focus on the evolution of approaches from traditional machine learning and deep learning models to the more advanced Transformer-based architectures. We systematically analyze over 100 studies, comparing the effectiveness, computational requirements, and applicability of various techniques, including Support Vector Machines, Long Short-Term Memory networks, Convolutional Neural Networks, and Transformer models like BERT and its multilingual variants. The review also explores the datasets, languages, and sources used for hate speech detection, noting the predominance of English-focused research while highlighting emerging efforts in low-resource languages and cross-lingual detection using multilingual Transformers. Additionally, we discuss the role of generative and multi-task learning models as promising avenues for future development. While Transformer-based models consistently achieve state-of-the-art performance, this review underscores the trade-offs between performance and computational cost, emphasizing the need for context-specific solutions. Key challenges such as algorithmic bias, data scarcity, and the need for more standardized benchmarks are also identified. This review provides crucial insights for advancing the field of hate speech detection and shaping future research directions.
- Open Access
- 18 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 101374-101389
Leveraging Transfer Learning for Hate Speech Detection in Portuguese Social Media Posts
The rapid rise of social media has brought about new ways of digital communication, along with a worrying increase in online hate speech (HS), which, in turn, has led researchers to develop several Natural Language Processing methods for its detection. Although significant strides have been made in automating HS detection, research focusing on the European Portuguese language remains scarce (as it happens in several under-resourced languages). To address this gap, we explore the efficacy of various transfer learning models, which have been shown in the literature to have better performance for this task than other Deep Learning models. We employ BERT-like models pre-trained on Portuguese text, such as BERTimbau and mDeBERTa, as well as GPT, Gemini and Mistral generative models, for the detection of HS within Portuguese online discourse. Our study relies on two annotated corpora of YouTube comments and tweets, both annotated as HS and non-HS. Our findings show that the best model for the YouTube corpus was a variant of BERTimbau retrained with European Portuguese tweets and fine-tuned for the HS task, with an F-score of 87.1% for the positive class, outperforming the baseline models by more than 20% and with a 1.8% increase compared with base BERTimbau. The best model for the Twitter corpus was GPT-3.5, with an F-score of 50.2% for the positive class. We also assess the impact of using in-domain and mixed-domain training sets, as well as the impact of providing context in generative model prompts on their performance.
- 18 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 101374-101389
Open AccessLeveraging Transfer Learning for Hate Speech Detection in Portuguese Social Media Posts
The rapid rise of social media has brought about new ways of digital communication, along with a worrying increase in online hate speech (HS), which, in turn, has led researchers to develop several Natural Language Processing methods for its detection. Although significant strides have been made in automating HS detection, research focusing on the European Portuguese language remains scarce (as it happens in several under-resourced languages). To address this gap, we explore the efficacy of various transfer learning models, which have been shown in the literature to have better performance for this task than other Deep Learning models. We employ BERT-like models pre-trained on Portuguese text, such as BERTimbau and mDeBERTa, as well as GPT, Gemini and Mistral generative models, for the detection of HS within Portuguese online discourse. Our study relies on two annotated corpora of YouTube comments and tweets, both annotated as HS and non-HS. Our findings show that the best model for the YouTube corpus was a variant of BERTimbau retrained with European Portuguese tweets and fine-tuned for the HS task, with an F-score of 87.1% for the positive class, outperforming the baseline models by more than 20% and with a 1.8% increase compared with base BERTimbau. The best model for the Twitter corpus was GPT-3.5, with an F-score of 50.2% for the positive class. We also assess the impact of using in-domain and mixed-domain training sets, as well as the impact of providing context in generative model prompts on their performance.
- Open Access
- 27 September 2022
- Published by Wiley in International Journal of Tourism Research
- Vol. 25 (1) , 123-136
Socio‐cultural impacts of peer‐to‐peer accommodation on host communities
Peer‐to‐peer accommodation has recently emerged as a central focus of research in tourism and hospitality. However, research on socio‐cultural impacts of peer‐to‐peer accommodation is fragmented. This study reviews the relevant literature on the socio‐cultural impacts of peer‐to‐peer accommodation on host communities and proposes an integrative framework and a working definition for goal socio‐cultural impacts of peer‐to‐peer accommodation. This literature review contributes to knowledge of how this business paradigm affects and frames host communities and integrates the factors that should be explored by researchers, policymakers, and organizations to manage the impacts of peer‐to‐peer accommodation on host communities.
- 27 September 2022
- Published by Wiley in International Journal of Tourism Research
- Vol. 25 (1) , 123-136
Open AccessSocio‐cultural impacts of peer‐to‐peer accommodation on host communities
Peer‐to‐peer accommodation has recently emerged as a central focus of research in tourism and hospitality. However, research on socio‐cultural impacts of peer‐to‐peer accommodation is fragmented. This study reviews the relevant literature on the socio‐cultural impacts of peer‐to‐peer accommodation on host communities and proposes an integrative framework and a working definition for goal socio‐cultural impacts of peer‐to‐peer accommodation. This literature review contributes to knowledge of how this business paradigm affects and frames host communities and integrates the factors that should be explored by researchers, policymakers, and organizations to manage the impacts of peer‐to‐peer accommodation on host communities.
- 4 October 2021
- Published by SAGE Publications in Journal of Creative Communications
- Vol. 16 (3) , 285-302
Instagram: A Gimmick or a Serious Reputation Builder in the Airline Business?
The purpose of the research was to shed light on the interrelatedness between Instagram and corporate reputation, on the one hand, and customer service expectations, on the other. A conceptual model was proposed to be tested in the context of the civil aviation economy. A national flagship airline company was chosen in which to conduct the research. An online questionnaire was made available, and 283 responses were collected. Partial least squares structural equation modelling (PLS SEM) was used to test the research hypotheses derived from the literature. The novelty of the work is in the scarce research found when scrutinising the literature on possible links between Instagram and airline corporate reputation. The study found a positive correlation between social media usage and corporate reputation in the airline sector. Future research needs to replicate this study across other airlines to ascertain the external validity of the current study and its potential for extrapolation.
- 4 October 2021
- Published by SAGE Publications in Journal of Creative Communications
- Vol. 16 (3) , 285-302
Instagram: A Gimmick or a Serious Reputation Builder in the Airline Business?
The purpose of the research was to shed light on the interrelatedness between Instagram and corporate reputation, on the one hand, and customer service expectations, on the other. A conceptual model was proposed to be tested in the context of the civil aviation economy. A national flagship airline company was chosen in which to conduct the research. An online questionnaire was made available, and 283 responses were collected. Partial least squares structural equation modelling (PLS SEM) was used to test the research hypotheses derived from the literature. The novelty of the work is in the scarce research found when scrutinising the literature on possible links between Instagram and airline corporate reputation. The study found a positive correlation between social media usage and corporate reputation in the airline sector. Future research needs to replicate this study across other airlines to ascertain the external validity of the current study and its potential for extrapolation.
- 4 May 2020
- Published by Springer Nature in Reading and Writing
- Vol. 33 (10) , 2459-2479
Lexical and sublexical orthographic knowledge: relationships in an orthography of intermediate depth
- 4 May 2020
- Published by Springer Nature in Reading and Writing
- Vol. 33 (10) , 2459-2479
Lexical and sublexical orthographic knowledge: relationships in an orthography of intermediate depth
- 30 November 2019
- Published by Taylor & Francis in Current Issues in Tourism
- Vol. 25 (19) , 3106-3109
Positioning Airbnb and Fairbnb in the sharing-exchange continuum
Many organizations are positioning themselves as part of the sharing economy due to positive connotations associated with the sharing concept. Recognizing that many of these organizations represent the sharing economy to varying degrees, this study selected two organizations – Airbnb and Fairbnb, to analyze the extent to which they serve as examples of the sharing economy. A content analysis was undertaken to identify the position of each organization on a continuum, ranging from pure sharing to pure exchange characteristics. The analysis reveals that overall Fairbnb may be a stronger example of the sharing economy than Airbnb.
- 30 November 2019
- Published by Taylor & Francis in Current Issues in Tourism
- Vol. 25 (19) , 3106-3109
Positioning Airbnb and Fairbnb in the sharing-exchange continuum
Many organizations are positioning themselves as part of the sharing economy due to positive connotations associated with the sharing concept. Recognizing that many of these organizations represent the sharing economy to varying degrees, this study selected two organizations – Airbnb and Fairbnb, to analyze the extent to which they serve as examples of the sharing economy. A content analysis was undertaken to identify the position of each organization on a continuum, ranging from pure sharing to pure exchange characteristics. The analysis reveals that overall Fairbnb may be a stronger example of the sharing economy than Airbnb.
- Open Access
- 1 December 2018
- Published by Elsevier in Journal of Destination Marketing & Management
- Vol. 10, 87-100
A multinational comparative study highlighting students' travel motivations and touristic trends
- 1 December 2018
- Published by Elsevier in Journal of Destination Marketing & Management
- Vol. 10, 87-100
Open AccessA multinational comparative study highlighting students' travel motivations and touristic trends