Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Advances in Computer, Signals and Systems
  4. Vol 7, Issue 2, 2023

Research on the Application of LSTM Neural Network Model in Text Sentiment Analysis and Sentiment Word Extraction

Download as PDF

DOI: 10.23977/acss.2023.070216 | Downloads: 14 | Views: 391

Author(s)

Junpeng Hu 1, Yegang Li 1

Affiliation(s)

1 School of Computer Science and Technology, Shandong University of Technology, Zibo, 255049 Shandong, China

Corresponding Author

Yegang Li

ABSTRACT

With the continuous development of neural network, many scholars who study natural language innovatively introduce neural network to improve the existing language model. This paper focuses on the application of LSTM (Long Short Term Memory) neural network model in text emotion analysis and emotion word extraction. A text emotion analysis model based on LSTM neural network model is proposed, which consists of two parts: LSTM and GCN (Graph convolution network). The LSTM model is used to effectively identify the fine-grained emotions in comments, and then the improved GCN is used to capture the structural information on the dependency graph, so as to realize the enhanced feature extraction of GCN emotional words, and finally realize the extraction of emotional words. The research results show that the accuracy of the improved algorithm proposed in this paper reaches 90% in the recognition of four emotional tendency categories, which proves the feasibility of the improved algorithm.

KEYWORDS

LSTM, GCN, Emotional analysis, Fine-grained emotion

CITE THIS PAPER

Junpeng Hu, Yegang Li. Research on the Application of LSTM Neural Network Model in Text Sentiment Analysis and Sentiment Word Extraction. Advances in Computer, Signals and Systems (2023) Vol. 7: 112-117. DOI: http://dx.doi.org/10.23977/acss.2023.070216.

REFERENCES

[1] Huang F, Zhang X, Zhao Z, et al. Image-text sentiment analysis via deep multimodal attentive fusion. Knowledge-Based Systems, vol. 167, no. 1, pp. 26-37, 2019.
[2] Bakar M, Idris N, Shuib L, et al. Sentiment Analysis of Noisy Malay Text: State of Art, Challenges and Future Work. IEEE Access, vol. 10, no. 99, pp. 1-1, 2020.
[3] Nawaz A, Awan A A, Ali T, et al. Product's behaviour recommendations using free text: an aspect based sentiment analysis approach. Cluster computing, vol. 23, no. 2, pp. 23, 2020.
[4] Jain A, Nandi B P, Gupta C, et al. Senti-NSetPSO: large-sized document-level sentiment analysis using Neutrosophic Set and particle swarm optimization. Soft Computing, vol. 24, no. 1, pp. 3-15, 2020.
[5] Martins R, Almeida J J, Henriques P, et al. A sentiment analysis approach to increase authorship identification. Expert Systems, vol. 17, no. 2, pp. 12469, 2019.
[6] Ma X, Zeng J, Peng L, et al. Modeling multi-aspects within one opinionated sentence simultaneously for aspect-level sentiment analysis. Future generation computer systems, vol. 93, no. 11, pp. 304-311, 2019.
[7] Lu X, Zhang H. Sentiment Analysis Method of Network Text Based on Improved AT-BiGRU Model. Scientific Programming, vol. 2021, no. 12, pp. 1-11, 2021.
[8] Long F, Zhou K, Ou W. Sentiment Analysis of Text Based on Bidirectional LSTM with Multi-head Attention. IEEE Access, vol. 66, no. 99, pp. 1-1, 2019.
[9] Ahmad S R, Bakar A A, Yaaku M R. Ant colony optimization for text feature selection in sentiment analysis. Intelligent Data Analysis, vol. 23, no. 1, pp. 133-158, 2019.
[10] Lee G T, Chang O K, Min S. Semisupervised sentiment analysis method for online text reviews. Journal of Information Science, vol. 47, no. 3, pp. 3, 2020.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 13688
Visits: 260517

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.