Abstractive Summarizers Become Emotional on News Summarization

[EN] Emotions are central to understanding contemporary journalism; however, they are overlooked in automatic news summarization. Actually, summaries are an entry point to the source article that could favor some emotions to captivate the reader. Nevertheless, the emotional content of summarization...

ver descrição completa

Detalhes bibliográficos
Autores: Ahuir-Esteve, Vicent|||0000-0001-5636-651X, Hurtado Oliver, Lluis Felip|||0000-0002-1877-0455, González, José-Ángel, Segarra Soriano, Encarnación
Formato: artículo
Fecha de publicación:2024
País:España
Recursos:Universitat Politècnica de València (UPV)
Repositorio:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:inglés
OAI Identifier:oai:riunet.upv.es:10251/204423
Acesso em linha:https://riunet.upv.es/handle/10251/204423
Access Level:acceso abierto
Palavra-chave:News summarization
Abstractive summarization
Emotional content
Emotional behavior
LENGUAJES Y SISTEMAS INFORMATICOS
Descrição
Resumo:[EN] Emotions are central to understanding contemporary journalism; however, they are overlooked in automatic news summarization. Actually, summaries are an entry point to the source article that could favor some emotions to captivate the reader. Nevertheless, the emotional content of summarization corpora and the emotional behavior of summarization models are still unexplored. In this work, we explore the usage of established methodologies to study the emotional content of summarization corpora and the emotional behavior of summarization models. Using these methodologies, we study the emotional content of two widely used summarization corpora: Cnn/Dailymail and Xsum, and the capabilities of three state-of-the-art transformer-based abstractive systems for eliciting emotions in the generated summaries: Bart, Pegasus, and T5. The main significant findings are as follows: (i) emotions are persistent in the two summarization corpora, (ii) summarizers approach moderately well the emotions of the reference summaries, and (iii) more than 75% of the emotions introduced by novel words in generated summaries are present in the reference ones. The combined use of these methodologies has allowed us to conduct a satisfactory study of the emotional content in news summarization.