Cookies
O website necessita de alguns cookies e outros recursos semelhantes para funcionar. Caso o permita, o INESC TEC irá utilizar cookies para recolher dados sobre as suas visitas, contribuindo, assim, para estatísticas agregadas que permitem melhorar o nosso serviço. Ver mais
Aceitar Rejeitar
  • Menu
Tópicos
de interesse
Detalhes

Detalhes

  • Nome

    Evelin Freire Amorim
  • Cargo

    Investigador Auxiliar
  • Desde

    21 setembro 2020
002
Publicações

2024

Keywords attention for fake news detection using few positive labels

Autores
de Souza, MC; Golo, MPS; Jorge, AMG; de Amorim, ECF; Campos, RNT; Marcacini, RM; Rezende, SO;

Publicação
INFORMATION SCIENCES

Abstract
Fake news detection (FND) tools are essential to increase the reliability of information in social media. FND can be approached as a machine learning classification problem so that discriminative features can be automatically extracted. However, this requires a large news set, which in turn implies a considerable amount of human experts' effort for labeling. In this paper, we explore Positive and Unlabeled Learning (PUL) to reduce the labeling cost. In particular, we improve PUL with the network-based Label Propagation (PU-LP) algorithm. PU-LP achieved competitive results in FND exploiting relations between news and terms and using few labeled fake news. We propose integrating an attention mechanism in PU-LP that can define which terms in the network are more relevant for detecting fake news. We use GNEE, a state-of-the-art algorithm based on graph attention networks. Our proposal outperforms state-of-the-art methods, improving F-1 in 2% to 10%, especially when only 10% labeled fake news are available. It is competitive with the binary baseline, even when nearly half of the data is labeled. Discrimination ability is also visualized through t-SNE. We also present an analysis of the limitations of our approach according to the type of text found in each dataset.

2024

Identification of Participants of Narratives Using Knowledge Bases

Autores
Machado, J; Amorim, E;

Publicação
Anais do XXXIX Simpósio Brasileiro de Banco de Dados (SBBD 2024)

Abstract
Identifying participants in narratives is important to understand and extract meaning from unstructured texts. This paper investigates the use of DBpedia and Wikifier for this task. We tested these two knowledge base platforms to evaluate their performance in recognizing and extracting entities in Portuguese-language journalistic narrative texts. The results show that both DBpedia and Wikifier present similar results in identifying participants, around 0.40 in the f1-score. The objective of this paper is to study the potential of knowledge bases to improve the understanding of narratives, in addition to suggesting directions for future research in this domain.

2023

Annotation and Visualisation of Reporting Events in Textual Narratives

Autores
Silvano, P; Amorim, E; Leal, A; Cantante, I; Silva, F; Jorge, A; Campos, R; Nunes, S;

Publicação
Proceedings of Text2Story - Sixth Workshop on Narrative Extraction From Texts held in conjunction with the 45th European Conference on Information Retrieval (ECIR 2023), Dublin, Ireland, April 2, 2023.

Abstract
News articles typically include reporting events to inform on what happened. These reporting events are not part of the story being told but are nonetheless a relevant part of the news and can pose a challenge to the computational processing of news narratives. They compose a reporting narrative, which is the present study's focus. This paper aims to demonstrate through selected use cases how a comprehensive annotation scheme with suitable tags and links can properly represent the reporting events and the way they relate to the events that make the story. In addition, we put forward a proposal for their visual representation that enables a systematic and detailed analysis of the importance of reporting events in the news structure. Finally, we describe some lexico-grammatical features of reporting events, which can contribute to their automatic detection. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

2023

A survey on narrative extraction from textual data

Autores
Santana, B; Campos, R; Amorim, E; Jorge, A; Silvano, P; Nunes, S;

Publicação
ARTIFICIAL INTELLIGENCE REVIEW

Abstract
Narratives are present in many forms of human expression and can be understood as a fundamental way of communication between people. Computational understanding of the underlying story of a narrative, however, may be a rather complex task for both linguists and computational linguistics. Such task can be approached using natural language processing techniques to automatically extract narratives from texts. In this paper, we present an in depth survey of narrative extraction from text, providing a establishing a basis/framework for the study roadmap to the study of this area as a whole as a means to consolidate a view on this line of research. We aim to fulfill the current gap by identifying important research efforts at the crossroad between linguists and computer scientists. In particular, we highlight the importance and complexity of the annotation process, as a crucial step for the training stage. Next, we detail methods and approaches regarding the identification and extraction of narrative components, their linkage and understanding of likely inherent relationships, before detailing formal narrative representation structures as an intermediate step for visualization and data exploration purposes. We then move into the narrative evaluation task aspects, and conclude this survey by highlighting important open issues under the domain of narratives extraction from texts that are yet to be explored.

2023

Mapeamento do Perfil das Mulheres Brasileiras em Processamento de Linguagem Natural

Autores
Caseli, H; Amorim, E; Schneider, ETR; Freitas, LIA; Rodrigues, J; Nunes, MdGV;

Publicação
Anais do XVII Women in Information Technology (WIT 2023)

Abstract
Conhecer o perfil das mulheres brasileiras que atuam em Processamento de Linguagem Natural (PLN) é um importante passo para o desenvolvimento de políticas e programas que visem aumentar a inclusão e a diversidade nessa área. Este é o primeiro trabalho realizado no Brasil com este fim. A partir de dados coletados via consulta pública, Lattes e Linkedin, notou-se que o perfil é de uma formação em computação ou linguística, atuando em empresas ou universidades, mas com pouca diversidade étnica e aparente dificuldade em conciliar vida profissional e maternidade. Analisando mais especificamente o grupo “Brasileiras em PLN” constatou-se uma expressiva capacidade de publicação e orientação, mas ainda uma baixa colaboração entre nossas integrantes.