The Importance of Context for Sentiment Analysis in Dialogues
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 human-computer interaction. For instance, in case of negative sentiment, the system may switch to a human operator who can h...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10216289/ |
_version_ | 1797739744414662656 |
---|---|
author | Isabel Carvalho Hugo Goncalo Oliveira Catarina Silva |
author_facet | Isabel Carvalho Hugo Goncalo Oliveira Catarina Silva |
author_sort | Isabel Carvalho |
collection | DOAJ |
description | 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 human-computer 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 human-computer 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. |
first_indexed | 2024-03-12T14:02:33Z |
format | Article |
id | doaj.art-364d958eb65d4668b6abbd29a3558a3c |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-03-12T14:02:33Z |
publishDate | 2023-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-364d958eb65d4668b6abbd29a3558a3c2023-08-21T23:00:54ZengIEEEIEEE Access2169-35362023-01-0111860888610310.1109/ACCESS.2023.330463310216289The Importance of Context for Sentiment Analysis in DialoguesIsabel Carvalho0https://orcid.org/0000-0002-9442-3439Hugo Goncalo Oliveira1https://orcid.org/0000-0002-5779-8645Catarina Silva2https://orcid.org/0000-0002-5656-0061Department of Informatics Engineering, Centre for Informatics and Systems of the University of Coimbra, University of Coimbra, Coimbra, PortugalDepartment of Informatics Engineering, Centre for Informatics and Systems of the University of Coimbra, University of Coimbra, Coimbra, PortugalDepartment of Informatics Engineering, Centre for Informatics and Systems of the University of Coimbra, University of Coimbra, Coimbra, PortugalSentiment 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 human-computer 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 human-computer 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.https://ieeexplore.ieee.org/document/10216289/Sentiment analysisdialogue analysiscontext awarenessnatural language processingdeep learningmachine learning |
spellingShingle | Isabel Carvalho Hugo Goncalo Oliveira Catarina Silva The Importance of Context for Sentiment Analysis in Dialogues IEEE Access Sentiment analysis dialogue analysis context awareness natural language processing deep learning machine learning |
title | The Importance of Context for Sentiment Analysis in Dialogues |
title_full | The Importance of Context for Sentiment Analysis in Dialogues |
title_fullStr | The Importance of Context for Sentiment Analysis in Dialogues |
title_full_unstemmed | The Importance of Context for Sentiment Analysis in Dialogues |
title_short | The Importance of Context for Sentiment Analysis in Dialogues |
title_sort | importance of context for sentiment analysis in dialogues |
topic | Sentiment analysis dialogue analysis context awareness natural language processing deep learning machine learning |
url | https://ieeexplore.ieee.org/document/10216289/ |
work_keys_str_mv | AT isabelcarvalho theimportanceofcontextforsentimentanalysisindialogues AT hugogoncalooliveira theimportanceofcontextforsentimentanalysisindialogues AT catarinasilva theimportanceofcontextforsentimentanalysisindialogues AT isabelcarvalho importanceofcontextforsentimentanalysisindialogues AT hugogoncalooliveira importanceofcontextforsentimentanalysisindialogues AT catarinasilva importanceofcontextforsentimentanalysisindialogues |