Paula Carvalho

Paula Carvalho

Auto-generated profile, based on publicly available information

Paula Carvalho

INESC-ID

Research Focus & Metrics

Academic Career Length

26Years (2001-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2016
Verified
Conference Paper
Open access
SASilvio Amir
Silvio Amir
BWByron C. Wallace
Byron C. Wallace
HLHao Lyu
Hao Lyu
PCPaula Carvalho
Paula Carvalho
MSMario J. Silva
Mario J. Silva

6 November 2009
Verified
Conference Paper
Open access
PCPaula Carvalho
Paula Carvalho
LSLuís Sarmento
Luís Sarmento
MSMário J. Silva
Mário J. Silva
EOEugénio Oliveira
Eugénio Oliveira
International audienceWe investigate the accuracy of a set of surface patterns in identifying ironic sentences in comments submitted by users to an on-line newspaper. The initial focus is on identifying irony in sentences containing positive predicates since these sentences are more exposed to irony, making their true po-larity harder to recognize. We show that it is possible to find ironic sentences with relatively high precision (from 45% to 85%) by exploring certain oral or gestural clues in user comments, such as emoticons, onomatopoeic expressions for laughter, heavy punctuation marks, quotation marks and positive interjections. We also demonstrate that clues based on deeper linguistic information are relatively inefficient in capturing irony in user-generated content, which points to the need for exploring additional types of oral clues

9 October 2024 in Social Network Analysis and Mining
Verified
Journal Article
Open access
PDF file
GRGil Ramos
Gil Ramos
FBFernando Batista
Fernando Batista
Ricardo RibeiroRicardo Ribeiro
Ricardo Ribeiro
PFPedro Fialho
Pedro Fialho
SMSérgio Moro
Sérgio Moro
CSCláudia Silva
Cláudia Silva
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.

1 January 2012 in Lecture Notes in Computer Science
Verified
Book Chapter
Closed access
PDF file
MSMário J. Silva
Mário J. Silva
PCPaula Carvalho
Paula Carvalho
LSLuís Sarmento
Luís Sarmento

19 June 2023 in Journal of Language Aggression and Conflict
Verified
Journal Article
Closed access
PCPaula Carvalho
Paula Carvalho
DCDanielle Caled
Danielle Caled
CSCláudia Silva
Cláudia Silva
FBFernando Batista
Fernando Batista
Ricardo RibeiroRicardo Ribeiro
Ricardo Ribeiro
This paper addresses the specificities of online hate speech against the Afro-descendant, Roma, and LGBTQ+ communities in Portugal. The research is based on the analysis of CO-HATE, a corpus composed of 20,590 YouTube comments, which were manually annotated following detailed guidelines created for that purpose. We applied methods from corpus linguistics to assess the prevalence of overt and covert hate speech, counter-speech, and offensive speech, considering different grounds of discrimination, and to investigate the main linguistic and rhetorical strategies underlying hatred messages. The research results highlight the importance of tackling covert hate speech, a recurring phenomenon often anchored in irony and fallacious argumentation, including the emotional appeal to fear and the implicit call to action. We believe this study will aid in advancing the analysis of online hate speech, while promoting the development of efficient automated detection models, specifically regarding the Portuguese language.

6 November 2009
Verified
Conference Paper
Open access
LSLuís Sarmento
Luís Sarmento
PCPaula Carvalho
Paula Carvalho
MSMário J. Silva
Mário J. Silva
EOEugénio Oliveira
Eugénio Oliveira
International audienceWe propose and evaluate a method for automatically cre-ating a reference corpus for training text classification pro-cedures for mining political opinions in user-generated con-tent. The process starts by compiling a collection of highly opinionated comments posted by users on an on-line news-paper. Then, we define and use a set of manually-crafted high-precision rules supported by a large sentiment-lexicon in order to identify sentences in each comment expressing opinions about political entities. Finally, the opinions found are propagated to the remainder sentences of the comment mentioning the same entities, thus increasing the number and variety of opinion-bearing sentences. Results show that most of the rules can identify negative opinions with very high precision, and these can be safely propagated to the remainder sentences in the comment in almost 100% of the cases. Due to problems arising from irony, the precision of identification drops for positive opinions, but several rules still reach high precision. Propagation of positive opinions is correct in about 77% of the cases, and most errors at this stage result from irony and polarity inversion throughout the comment