Utilize este identificador para referenciar este registo: https://hdl.handle.net/10316/114412
Título: The Importance of Context for Sentiment Analysis in Dialogues
Autor: Carvalho, Isabel 
Oliveira, Hugo Gonçalo 
Silva, Catarina 
Palavras-chave: Sentiment analysis; dialogue analysis; context awareness; natural language processing; deep learning; machine learning
Data: 2023
Editora: IEEE
Projeto: This work was supported in part by the Project FLOWANCE, Co-Financed by the European Regional Development Fund (FEDER), through Portugal 2020 (PT2020) under Grant POCI-01-0247-FEDER-047022; in part by the Competitiveness and Internationalization Operational Program (COMPETE 2020), Project POWER, Co-Financed by the European Regional Development Fund (FEDER), through Portugal 2020 (PT2020) under Grant POCI-01-0247-FEDER-070365; in part by the Portuguese Recovery and Resilience Plan (PRR) through project C645008882-00000055, Center for Responsible AI; in part by the Competitiveness and Internationalization Operational Program (COMPETE 2020); in part by the National funds through Foundation for Science and Technology (FCT), within the Scope of the Project Centre for Informatics and Systems of the University of Coimbra (CISUC) under Grant UID/CEC/00326/2020; and in part by the European Social Fund, through the Regional Operational Program Centro 2020. 
Título da revista, periódico, livro ou evento: IEEE Access
Volume: 11
Resumo: Sentiment Analysis (SA) can be applied to dialogues to determine the emotional tone throughout the conversation. This is beneficial for dialogue systems because it may improve humancomputer interaction. For instance, in case of negative sentiment, the system may switch to a human operator who can handle the situation more effectively. However, given that dialogues are a series of utterances, the context, including the previous text, plays a crucial role in analyzing the current sentiment. Our aim is to investigate the importance of context when monitoring the sentiment of every utterance during a conversation. To accomplish this goal, we assess sentiment analysis in dialogues with varying levels of context, specifically differing in the number and author of preceding utterances. We conduct experiments on Portuguese customer-support conversations, with each utterance manually labeled as having negative or non-negative sentiment.We test a wide range of text classification approaches, from traditional, as simplicity should not be overlooked, to more recent methods, as they are more likely to achieve better performances. Results indicate that the relevance of context varies. However, context assumes particular value in humancomputer dialogues, when considering both speakers, and in shorter human-human conversations, when focusing on the client. Moreover, the best classifier for both scenarios, based on BERT, achieves the highest scores when considering the context.
URI: https://hdl.handle.net/10316/114412
ISSN: 2169-3536
DOI: 10.1109/ACCESS.2023.3304633
Direitos: openAccess
Aparece nas coleções:I&D CISUC - Artigos em Revistas Internacionais
FCTUC Eng.Informática - Artigos em Revistas Internacionais

Ficheiros deste registo:
Ficheiro Descrição TamanhoFormato
The_Importance_of_Context_for_Sentiment_Analysis_in_Dialogues.pdf3.57 MBAdobe PDFVer/Abrir
Mostrar registo em formato completo

Visualizações de página

17
Visto em 8/mai/2024

Downloads

13
Visto em 8/mai/2024

Google ScholarTM

Verificar

Altmetric

Altmetric


Este registo está protegido por Licença Creative Commons Creative Commons