A Lightweight Sentiment Analysis Framework for a Micro-Intelligent Terminal
Sentiment analysis aims to mine polarity features in the text, which can empower intelligent terminals to recognize opinions and further enhance interaction capabilities with customers. Considerable progress has been made using recurrent neural networks or pre-trained models to learn semantic repres...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/2/741 |
| _version_ | 1797437304816533504 |
|---|---|
| author | Lin Wei Zhenyuan Wang Jing Xu Yucheng Shi Qingxian Wang Lei Shi Yongcai Tao Yufei Gao |
| author_facet | Lin Wei Zhenyuan Wang Jing Xu Yucheng Shi Qingxian Wang Lei Shi Yongcai Tao Yufei Gao |
| author_sort | Lin Wei |
| collection | DOAJ |
| description | Sentiment analysis aims to mine polarity features in the text, which can empower intelligent terminals to recognize opinions and further enhance interaction capabilities with customers. Considerable progress has been made using recurrent neural networks or pre-trained models to learn semantic representations. However, recently published models with complex structures require increasing computational resources to reach state-of-the-art (SOTA) performance. It is still a significant challenge to deploy these models to run on micro-intelligent terminals with limited computing power and memory. This paper proposes a lightweight and efficient framework based on hybrid multi-grained embedding on sentiment analysis (MC-GGRU). The gated recurrent unit model is designed to incorporate a global attention structure that allows contextual representations to be learned from unstructured text using word tokens. In addition, a multi-grained feature layer can further enrich sentence representation features with implicit semantics from characters. Through hybrid multi-grained representation, MC-GGRU achieves high inference performance with a shallow structure. The experimental results of five public datasets show that our method achieves SOTA for sentiment classification with a trade-off between accuracy and speed. |
| first_indexed | 2024-03-09T11:18:15Z |
| format | Article |
| id | doaj.art-757f2e19937b476b890050315a9ae7fd |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T11:18:15Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-757f2e19937b476b890050315a9ae7fd2023-12-01T00:26:47ZengMDPI AGSensors1424-82202023-01-0123274110.3390/s23020741A Lightweight Sentiment Analysis Framework for a Micro-Intelligent TerminalLin Wei0Zhenyuan Wang1Jing Xu2Yucheng Shi3Qingxian Wang4Lei Shi5Yongcai Tao6Yufei Gao7School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou 450001, ChinaCollege of Intelligence and Computing, Tianjin University, Tianjin 300072, ChinaSchool of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450001, ChinaSentiment analysis aims to mine polarity features in the text, which can empower intelligent terminals to recognize opinions and further enhance interaction capabilities with customers. Considerable progress has been made using recurrent neural networks or pre-trained models to learn semantic representations. However, recently published models with complex structures require increasing computational resources to reach state-of-the-art (SOTA) performance. It is still a significant challenge to deploy these models to run on micro-intelligent terminals with limited computing power and memory. This paper proposes a lightweight and efficient framework based on hybrid multi-grained embedding on sentiment analysis (MC-GGRU). The gated recurrent unit model is designed to incorporate a global attention structure that allows contextual representations to be learned from unstructured text using word tokens. In addition, a multi-grained feature layer can further enrich sentence representation features with implicit semantics from characters. Through hybrid multi-grained representation, MC-GGRU achieves high inference performance with a shallow structure. The experimental results of five public datasets show that our method achieves SOTA for sentiment classification with a trade-off between accuracy and speed.https://www.mdpi.com/1424-8220/23/2/741sentiment analysisglobal attentionmulti-grained representationlightweight |
| spellingShingle | Lin Wei Zhenyuan Wang Jing Xu Yucheng Shi Qingxian Wang Lei Shi Yongcai Tao Yufei Gao A Lightweight Sentiment Analysis Framework for a Micro-Intelligent Terminal Sensors sentiment analysis global attention multi-grained representation lightweight |
| title | A Lightweight Sentiment Analysis Framework for a Micro-Intelligent Terminal |
| title_full | A Lightweight Sentiment Analysis Framework for a Micro-Intelligent Terminal |
| title_fullStr | A Lightweight Sentiment Analysis Framework for a Micro-Intelligent Terminal |
| title_full_unstemmed | A Lightweight Sentiment Analysis Framework for a Micro-Intelligent Terminal |
| title_short | A Lightweight Sentiment Analysis Framework for a Micro-Intelligent Terminal |
| title_sort | lightweight sentiment analysis framework for a micro intelligent terminal |
| topic | sentiment analysis global attention multi-grained representation lightweight |
| url | https://www.mdpi.com/1424-8220/23/2/741 |
| work_keys_str_mv | AT linwei alightweightsentimentanalysisframeworkforamicrointelligentterminal AT zhenyuanwang alightweightsentimentanalysisframeworkforamicrointelligentterminal AT jingxu alightweightsentimentanalysisframeworkforamicrointelligentterminal AT yuchengshi alightweightsentimentanalysisframeworkforamicrointelligentterminal AT qingxianwang alightweightsentimentanalysisframeworkforamicrointelligentterminal AT leishi alightweightsentimentanalysisframeworkforamicrointelligentterminal AT yongcaitao alightweightsentimentanalysisframeworkforamicrointelligentterminal AT yufeigao alightweightsentimentanalysisframeworkforamicrointelligentterminal AT linwei lightweightsentimentanalysisframeworkforamicrointelligentterminal AT zhenyuanwang lightweightsentimentanalysisframeworkforamicrointelligentterminal AT jingxu lightweightsentimentanalysisframeworkforamicrointelligentterminal AT yuchengshi lightweightsentimentanalysisframeworkforamicrointelligentterminal AT qingxianwang lightweightsentimentanalysisframeworkforamicrointelligentterminal AT leishi lightweightsentimentanalysisframeworkforamicrointelligentterminal AT yongcaitao lightweightsentimentanalysisframeworkforamicrointelligentterminal AT yufeigao lightweightsentimentanalysisframeworkforamicrointelligentterminal |