Aspect-Based Sentiment Analysis Using Aspect Map
Aspect-based sentiment analysis (ABSA) is the task of classifying the sentiment of a specific aspect in a text. Because a single text usually has multiple aspects which are expressed independently, ABSA is a crucial task for in-depth opinion mining. A key point of solving ABSA is to align sentiment...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/9/16/3239 |
| _version_ | 1818284396792250368 |
|---|---|
| author | Yunseok Noh Seyoung Park Seong-Bae Park |
| author_facet | Yunseok Noh Seyoung Park Seong-Bae Park |
| author_sort | Yunseok Noh |
| collection | DOAJ |
| description | Aspect-based sentiment analysis (ABSA) is the task of classifying the sentiment of a specific aspect in a text. Because a single text usually has multiple aspects which are expressed independently, ABSA is a crucial task for in-depth opinion mining. A key point of solving ABSA is to align sentiment expressions with their proper target aspect in a text. Thus, many recent neural models have applied attention mechanisms to learning the alignment. However, it is problematic to depend solely on attention mechanisms to achieve this, because most sentiment expressions such as “<i>nice</i>” and “<i>bad</i>” are too general to be aligned with a proper aspect even through an attention mechanism. To solve this problem, this paper proposes a novel convolutional neural network (CNN)-based aspect-level sentiment classification model, which consists of two CNNs. Because sentiment expressions relevant to an aspect usually appear near the aspect expressions of the aspect, the proposed model first finds the aspect expressions for a given aspect and then focuses on the sentiment expressions around the aspect expressions to determine the final sentiment of an aspect. Thus, the first CNN extracts the positional information of aspect expressions for a target aspect and expresses the information as an aspect map. Even if there exist no data with annotations on direct relation between aspects and their expressions, the aspect map can be obtained effectively by learning it in a weakly supervised manner. Then, the second CNN classifies the sentiment of the target aspect in a text using the aspect map. The proposed model is evaluated on SemEval 2016 Task 5 dataset and is compared with several baseline models. According to the experimental results, the proposed model does not only outperform the baseline models but also shows state-of-the-art performance for the dataset. |
| first_indexed | 2024-12-13T00:52:09Z |
| format | Article |
| id | doaj.art-1516aa92a827483ab18d17f269933cdd |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-13T00:52:09Z |
| publishDate | 2019-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-1516aa92a827483ab18d17f269933cdd2022-12-22T00:04:54ZengMDPI AGApplied Sciences2076-34172019-08-01916323910.3390/app9163239app9163239Aspect-Based Sentiment Analysis Using Aspect MapYunseok Noh0Seyoung Park1Seong-Bae Park2School of Computer Science and Engineering, Kyungpook National University, Daegu 702-701, KoreaSchool of Computer Science and Engineering, Kyungpook National University, Daegu 702-701, KoreaDepartment of Computer Science and Engineering, Kyung Hee University, Yongin-si, Gyeonggi-do 17104, KoreaAspect-based sentiment analysis (ABSA) is the task of classifying the sentiment of a specific aspect in a text. Because a single text usually has multiple aspects which are expressed independently, ABSA is a crucial task for in-depth opinion mining. A key point of solving ABSA is to align sentiment expressions with their proper target aspect in a text. Thus, many recent neural models have applied attention mechanisms to learning the alignment. However, it is problematic to depend solely on attention mechanisms to achieve this, because most sentiment expressions such as “<i>nice</i>” and “<i>bad</i>” are too general to be aligned with a proper aspect even through an attention mechanism. To solve this problem, this paper proposes a novel convolutional neural network (CNN)-based aspect-level sentiment classification model, which consists of two CNNs. Because sentiment expressions relevant to an aspect usually appear near the aspect expressions of the aspect, the proposed model first finds the aspect expressions for a given aspect and then focuses on the sentiment expressions around the aspect expressions to determine the final sentiment of an aspect. Thus, the first CNN extracts the positional information of aspect expressions for a target aspect and expresses the information as an aspect map. Even if there exist no data with annotations on direct relation between aspects and their expressions, the aspect map can be obtained effectively by learning it in a weakly supervised manner. Then, the second CNN classifies the sentiment of the target aspect in a text using the aspect map. The proposed model is evaluated on SemEval 2016 Task 5 dataset and is compared with several baseline models. According to the experimental results, the proposed model does not only outperform the baseline models but also shows state-of-the-art performance for the dataset.https://www.mdpi.com/2076-3417/9/16/3239aspect-based sentiment analysisclass activation mappingconvolutional neural networksopinion miningweakly supervised learning |
| spellingShingle | Yunseok Noh Seyoung Park Seong-Bae Park Aspect-Based Sentiment Analysis Using Aspect Map Applied Sciences aspect-based sentiment analysis class activation mapping convolutional neural networks opinion mining weakly supervised learning |
| title | Aspect-Based Sentiment Analysis Using Aspect Map |
| title_full | Aspect-Based Sentiment Analysis Using Aspect Map |
| title_fullStr | Aspect-Based Sentiment Analysis Using Aspect Map |
| title_full_unstemmed | Aspect-Based Sentiment Analysis Using Aspect Map |
| title_short | Aspect-Based Sentiment Analysis Using Aspect Map |
| title_sort | aspect based sentiment analysis using aspect map |
| topic | aspect-based sentiment analysis class activation mapping convolutional neural networks opinion mining weakly supervised learning |
| url | https://www.mdpi.com/2076-3417/9/16/3239 |
| work_keys_str_mv | AT yunseoknoh aspectbasedsentimentanalysisusingaspectmap AT seyoungpark aspectbasedsentimentanalysisusingaspectmap AT seongbaepark aspectbasedsentimentanalysisusingaspectmap |