EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Lightweight Sentiment Analysis Framework for a Micro-Intelligent Terminal

Lin Wei, Zhenyuan Wang, Jing Xu, Yucheng Shi, Qingxian Wang, Lei Shi iD, Yongcai Tao, Yufei Gao

Sensors · 2023

DOI: 10.3390/s23020741 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Lin Wei und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450001, China. Hauptthemen laut MEDLINE: Sentiment Analysis, Semantics. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Key Technologies R&D Program, the Nature Science Foundation of China, the Key Project of Public Benefit in Henan Province of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Sentiment AnalysisSemanticsLanguageNeural Networks, ComputerMachine Learning

Stichwörter der Autor:innen

global attentionlightweightmulti-grained representationsentiment analysis

Autor:innen und Institutionen

  • School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450001, China.
  • Songshan Laboratory, Zhengzhou 450018, China.
  • School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou 450001, China.
  • College of Intelligence and Computing, Tianjin University, Tianjin 300072, China.

ORCID-Profile: Lei Shi

Förderung

  • the National Key Technologies R&D Program
  • the Nature Science Foundation of China
  • the Key Project of Public Benefit in Henan Province of China
  • the Key Scientific and Technology Project of Henan Province of China
  • the Research Foundation for Advanced Talents of Zhengzhou University
  • the Key Research Projects of Universities in Henan Province of China
  • the Fundamental Science Projects of Railway Police College
  • the Key Scientific and Technological Research Projects in Henan Province of China

Zitieren

APA

Wei, L., Wang, Z., Xu, J., Shi, Y., Wang, Q., Shi, L., Tao, Y., & Gao, Y. (2023). A Lightweight Sentiment Analysis Framework for a Micro-Intelligent Terminal. Sensors. https://doi.org/10.3390/s23020741

Vancouver

Wei L, Wang Z, Xu J, Shi Y, Wang Q, Shi L, et al. A Lightweight Sentiment Analysis Framework for a Micro-Intelligent Terminal. Sensors. 2023. doi:10.3390/s23020741

BibTeX
@article{Wei2023,
  author = {Wei, Lin and Wang, Zhenyuan and Xu, Jing and Shi, Yucheng and Wang, Qingxian and Shi, Lei and Tao, Yongcai and Gao, Yufei},
  title = {A Lightweight Sentiment Analysis Framework for a Micro-Intelligent Terminal},
  journal = {Sensors},
  year = {2023},
  doi = {10.3390/s23020741}
}
Kostenlos starten →