Sentiment Analysis of Chinese Product Reviews Based on Fusion of DUAL-Channel BiLSTM and Self-Attention
Product reviews provide crucial information for both consumers and businesses, offering insights needed before purchasing a product or service. However, existing sentiment analysis methods, especially for Chinese language, struggle to effectively capture contextual information due to the complex sem...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Future Internet |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-5903/15/11/364 |
| _version_ | 1797459298294431744 |
|---|---|
| author | Ye Yuan Wang Wang Guangze Wen Zikun Zheng Zhemin Zhuang |
| author_facet | Ye Yuan Wang Wang Guangze Wen Zikun Zheng Zhemin Zhuang |
| author_sort | Ye Yuan |
| collection | DOAJ |
| description | Product reviews provide crucial information for both consumers and businesses, offering insights needed before purchasing a product or service. However, existing sentiment analysis methods, especially for Chinese language, struggle to effectively capture contextual information due to the complex semantics, multiple sentiment polarities, and long-term dependencies between words. In this paper, we propose a sentiment classification method based on the BiLSTM algorithm to address these challenges in natural language processing. Self-Attention-CNN BiLSTM (SAC-BiLSTM) leverages dual channels to extract features from both character-level embeddings and word-level embeddings. It combines BiLSTM and Self-Attention mechanisms for feature extraction and weight allocation, aiming to overcome the limitations in mining contextual information. Experiments were conducted on the onlineshopping10cats dataset, which is a standard corpus of e-commerce shopping reviews available in the ChineseNlpCorpus 2018. The experimental results demonstrate the effectiveness of our proposed algorithm, with Recall, Precision, and F1 scores reaching 0.9409, 0.9369, and 0.9404, respectively. |
| first_indexed | 2024-03-09T16:49:26Z |
| format | Article |
| id | doaj.art-fd6992569d8f4bbc86a857836447f6e6 |
| institution | Directory Open Access Journal |
| issn | 1999-5903 |
| language | English |
| last_indexed | 2024-03-09T16:49:26Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Future Internet |
| spelling | doaj.art-fd6992569d8f4bbc86a857836447f6e62023-11-24T14:43:12ZengMDPI AGFuture Internet1999-59032023-11-01151136410.3390/fi15110364Sentiment Analysis of Chinese Product Reviews Based on Fusion of DUAL-Channel BiLSTM and Self-AttentionYe Yuan0Wang Wang1Guangze Wen2Zikun Zheng3Zhemin Zhuang4College of Engineering, Shantou University, Shantou 515063, ChinaCollege of Engineering, Shantou University, Shantou 515063, ChinaCollege of Engineering, Shantou University, Shantou 515063, ChinaCollege of Engineering, Shantou University, Shantou 515063, ChinaCollege of Engineering, Shantou University, Shantou 515063, ChinaProduct reviews provide crucial information for both consumers and businesses, offering insights needed before purchasing a product or service. However, existing sentiment analysis methods, especially for Chinese language, struggle to effectively capture contextual information due to the complex semantics, multiple sentiment polarities, and long-term dependencies between words. In this paper, we propose a sentiment classification method based on the BiLSTM algorithm to address these challenges in natural language processing. Self-Attention-CNN BiLSTM (SAC-BiLSTM) leverages dual channels to extract features from both character-level embeddings and word-level embeddings. It combines BiLSTM and Self-Attention mechanisms for feature extraction and weight allocation, aiming to overcome the limitations in mining contextual information. Experiments were conducted on the onlineshopping10cats dataset, which is a standard corpus of e-commerce shopping reviews available in the ChineseNlpCorpus 2018. The experimental results demonstrate the effectiveness of our proposed algorithm, with Recall, Precision, and F1 scores reaching 0.9409, 0.9369, and 0.9404, respectively.https://www.mdpi.com/1999-5903/15/11/364natural language processingsentiment classificationBiLSTMself-attentionscalable multi-channel |
| spellingShingle | Ye Yuan Wang Wang Guangze Wen Zikun Zheng Zhemin Zhuang Sentiment Analysis of Chinese Product Reviews Based on Fusion of DUAL-Channel BiLSTM and Self-Attention Future Internet natural language processing sentiment classification BiLSTM self-attention scalable multi-channel |
| title | Sentiment Analysis of Chinese Product Reviews Based on Fusion of DUAL-Channel BiLSTM and Self-Attention |
| title_full | Sentiment Analysis of Chinese Product Reviews Based on Fusion of DUAL-Channel BiLSTM and Self-Attention |
| title_fullStr | Sentiment Analysis of Chinese Product Reviews Based on Fusion of DUAL-Channel BiLSTM and Self-Attention |
| title_full_unstemmed | Sentiment Analysis of Chinese Product Reviews Based on Fusion of DUAL-Channel BiLSTM and Self-Attention |
| title_short | Sentiment Analysis of Chinese Product Reviews Based on Fusion of DUAL-Channel BiLSTM and Self-Attention |
| title_sort | sentiment analysis of chinese product reviews based on fusion of dual channel bilstm and self attention |
| topic | natural language processing sentiment classification BiLSTM self-attention scalable multi-channel |
| url | https://www.mdpi.com/1999-5903/15/11/364 |
| work_keys_str_mv | AT yeyuan sentimentanalysisofchineseproductreviewsbasedonfusionofdualchannelbilstmandselfattention AT wangwang sentimentanalysisofchineseproductreviewsbasedonfusionofdualchannelbilstmandselfattention AT guangzewen sentimentanalysisofchineseproductreviewsbasedonfusionofdualchannelbilstmandselfattention AT zikunzheng sentimentanalysisofchineseproductreviewsbasedonfusionofdualchannelbilstmandselfattention AT zheminzhuang sentimentanalysisofchineseproductreviewsbasedonfusionofdualchannelbilstmandselfattention |