Improving Document-Level Sentiment Classification Using Importance of Sentences
Previous researchers have considered sentiment analysis as a document classification task, in which input documents are classified into predefined sentiment classes. Although there are sentences in a document that support important evidences for sentiment analysis and sentences that do not, they hav...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-11-01
|
Series: | Entropy |
Subjects: | |
Online Access: | https://www.mdpi.com/1099-4300/22/12/1336 |
_version_ | 1797546865409916928 |
---|---|
author | Gihyeon Choi Shinhyeok Oh Harksoo Kim |
author_facet | Gihyeon Choi Shinhyeok Oh Harksoo Kim |
author_sort | Gihyeon Choi |
collection | DOAJ |
description | Previous researchers have considered sentiment analysis as a document classification task, in which input documents are classified into predefined sentiment classes. Although there are sentences in a document that support important evidences for sentiment analysis and sentences that do not, they have treated the document as a bag of sentences. In other words, they have not considered the importance of each sentence in the document. To effectively determine polarity of a document, each sentence in the document should be dealt with different degrees of importance. To address this problem, we propose a document-level sentence classification model based on deep neural networks, in which the importance degrees of sentences in documents are automatically determined through gate mechanisms. To verify our new sentiment analysis model, we conducted experiments using the sentiment datasets in the four different domains such as movie reviews, hotel reviews, restaurant reviews, and music reviews. In the experiments, the proposed model outperformed previous state-of-the-art models that do not consider importance differences of sentences in a document. The experimental results show that the importance of sentences should be considered in a document-level sentiment classification task. |
first_indexed | 2024-03-10T14:35:17Z |
format | Article |
id | doaj.art-bc6896314c93476dace194541ff062e0 |
institution | Directory Open Access Journal |
issn | 1099-4300 |
language | English |
last_indexed | 2024-03-10T14:35:17Z |
publishDate | 2020-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Entropy |
spelling | doaj.art-bc6896314c93476dace194541ff062e02023-11-20T22:14:25ZengMDPI AGEntropy1099-43002020-11-012212133610.3390/e22121336Improving Document-Level Sentiment Classification Using Importance of SentencesGihyeon Choi0Shinhyeok Oh1Harksoo Kim2Program of Computer and Communications Engineering, College of IT, Kangwon National University, Chuncheon-si 24341, KoreaProgram of Computer and Communications Engineering, College of IT, Kangwon National University, Chuncheon-si 24341, KoreaDivision of Computer Science and Engineering & Department of Artificial Intelligence, College of Engineering, Konkuk University, 120 Neungdong-ro, Gwangjin-gu, Seoul 05029, KoreaPrevious researchers have considered sentiment analysis as a document classification task, in which input documents are classified into predefined sentiment classes. Although there are sentences in a document that support important evidences for sentiment analysis and sentences that do not, they have treated the document as a bag of sentences. In other words, they have not considered the importance of each sentence in the document. To effectively determine polarity of a document, each sentence in the document should be dealt with different degrees of importance. To address this problem, we propose a document-level sentence classification model based on deep neural networks, in which the importance degrees of sentences in documents are automatically determined through gate mechanisms. To verify our new sentiment analysis model, we conducted experiments using the sentiment datasets in the four different domains such as movie reviews, hotel reviews, restaurant reviews, and music reviews. In the experiments, the proposed model outperformed previous state-of-the-art models that do not consider importance differences of sentences in a document. The experimental results show that the importance of sentences should be considered in a document-level sentiment classification task.https://www.mdpi.com/1099-4300/22/12/1336sentiment analysisdocument-level classificationimportance of sentence |
spellingShingle | Gihyeon Choi Shinhyeok Oh Harksoo Kim Improving Document-Level Sentiment Classification Using Importance of Sentences Entropy sentiment analysis document-level classification importance of sentence |
title | Improving Document-Level Sentiment Classification Using Importance of Sentences |
title_full | Improving Document-Level Sentiment Classification Using Importance of Sentences |
title_fullStr | Improving Document-Level Sentiment Classification Using Importance of Sentences |
title_full_unstemmed | Improving Document-Level Sentiment Classification Using Importance of Sentences |
title_short | Improving Document-Level Sentiment Classification Using Importance of Sentences |
title_sort | improving document level sentiment classification using importance of sentences |
topic | sentiment analysis document-level classification importance of sentence |
url | https://www.mdpi.com/1099-4300/22/12/1336 |
work_keys_str_mv | AT gihyeonchoi improvingdocumentlevelsentimentclassificationusingimportanceofsentences AT shinhyeokoh improvingdocumentlevelsentimentclassificationusingimportanceofsentences AT harksookim improvingdocumentlevelsentimentclassificationusingimportanceofsentences |