Improving Implicit Sentiments Analysis via Explanations of Multiple Perspectives

Implicit sentiment expressions convey emotions indirectly, through context or factual statements, rather than explicit opinion words. Recent research on implicit sentiment analysis overlooks the fact that various individuals can interpret the same implicit expressions in different manners and experi...

Full description

Saved in:
Bibliographic Details
Main Authors: An Wang, Huidong Jiang, Youmi Ma, Junfeng Jiang, Ao Liu, Naoaki Okazaki
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10947047/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850185876122894336
author An Wang
Huidong Jiang
Youmi Ma
Junfeng Jiang
Ao Liu
Naoaki Okazaki
author_facet An Wang
Huidong Jiang
Youmi Ma
Junfeng Jiang
Ao Liu
Naoaki Okazaki
author_sort An Wang
collection DOAJ
description Implicit sentiment expressions convey emotions indirectly, through context or factual statements, rather than explicit opinion words. Recent research on implicit sentiment analysis overlooks the fact that various individuals can interpret the same implicit expressions in different manners and experience different sentiments. Additionally, most previous research mainly focuses on implicit sentiment classification, neglecting the reasons behind the results. It hinders the deep understanding of the complexities involved in human emotions and limits the application of sentiment analysis. In this work, we introduce a new task, Abisa-Ex, which aims at both sentiment classification and explanation generation. We re-labeled the previous aspect-based implicit sentiment analysis dataset, incorporating new (sentiment, explanation) pair labels provided by various annotators. Based on the new dataset, we design frameworks to allow models to learn to predict sentiments from different perspectives and provide reasonable explanations jointly. Notably, our work shows that learning explanations from various viewpoints not only allows the model to generate the logical process behind sentiment analysis, but also significantly improves the model’s sentiment classification performance.
format Article
id doaj-art-e6055ceaed7f4d4d8ca3f6854e78c392
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-e6055ceaed7f4d4d8ca3f6854e78c3922025-08-20T02:16:33ZengIEEEIEEE Access2169-35362025-01-0113611366114810.1109/ACCESS.2025.355676210947047Improving Implicit Sentiments Analysis via Explanations of Multiple PerspectivesAn Wang0https://orcid.org/0000-0001-8503-643XHuidong Jiang1https://orcid.org/0009-0003-3859-0536Youmi Ma2https://orcid.org/0000-0002-8576-7563Junfeng Jiang3Ao Liu4https://orcid.org/0000-0001-6785-6282Naoaki Okazaki5Department of Computer Science, Institute of Science Tokyo, Tokyo, JapanDepartment of Computer Science, Institute of Science Tokyo, Tokyo, JapanDepartment of Computer Science, Institute of Science Tokyo, Tokyo, JapanDepartment of Computer Science, The University of Tokyo, Tokyo, JapanTencent Inc., Shenzhen, ChinaDepartment of Computer Science, Institute of Science Tokyo, Tokyo, JapanImplicit sentiment expressions convey emotions indirectly, through context or factual statements, rather than explicit opinion words. Recent research on implicit sentiment analysis overlooks the fact that various individuals can interpret the same implicit expressions in different manners and experience different sentiments. Additionally, most previous research mainly focuses on implicit sentiment classification, neglecting the reasons behind the results. It hinders the deep understanding of the complexities involved in human emotions and limits the application of sentiment analysis. In this work, we introduce a new task, Abisa-Ex, which aims at both sentiment classification and explanation generation. We re-labeled the previous aspect-based implicit sentiment analysis dataset, incorporating new (sentiment, explanation) pair labels provided by various annotators. Based on the new dataset, we design frameworks to allow models to learn to predict sentiments from different perspectives and provide reasonable explanations jointly. Notably, our work shows that learning explanations from various viewpoints not only allows the model to generate the logical process behind sentiment analysis, but also significantly improves the model’s sentiment classification performance.https://ieeexplore.ieee.org/document/10947047/Sentiment analysisimplicit sentimentexplanation generation
spellingShingle An Wang
Huidong Jiang
Youmi Ma
Junfeng Jiang
Ao Liu
Naoaki Okazaki
Improving Implicit Sentiments Analysis via Explanations of Multiple Perspectives
IEEE Access
Sentiment analysis
implicit sentiment
explanation generation
title Improving Implicit Sentiments Analysis via Explanations of Multiple Perspectives
title_full Improving Implicit Sentiments Analysis via Explanations of Multiple Perspectives
title_fullStr Improving Implicit Sentiments Analysis via Explanations of Multiple Perspectives
title_full_unstemmed Improving Implicit Sentiments Analysis via Explanations of Multiple Perspectives
title_short Improving Implicit Sentiments Analysis via Explanations of Multiple Perspectives
title_sort improving implicit sentiments analysis via explanations of multiple perspectives
topic Sentiment analysis
implicit sentiment
explanation generation
url https://ieeexplore.ieee.org/document/10947047/
work_keys_str_mv AT anwang improvingimplicitsentimentsanalysisviaexplanationsofmultipleperspectives
AT huidongjiang improvingimplicitsentimentsanalysisviaexplanationsofmultipleperspectives
AT youmima improvingimplicitsentimentsanalysisviaexplanationsofmultipleperspectives
AT junfengjiang improvingimplicitsentimentsanalysisviaexplanationsofmultipleperspectives
AT aoliu improvingimplicitsentimentsanalysisviaexplanationsofmultipleperspectives
AT naoakiokazaki improvingimplicitsentimentsanalysisviaexplanationsofmultipleperspectives