Ayuda
Ir al contenido

Dialnet


A Sentiment Analysis Method Based on Bidirectional Long Short-Term Memory Networks

  • Autores: Haimei Zheng, Jian Xu, Lei Liting, Liu Jianxin, Riyad Alshalabi
  • Localización: Applied Mathematics and Nonlinear Sciences, ISSN-e 2444-8656, Vol. 8, Nº. 1, 2023, págs. 55-68
  • Idioma: inglés
  • Enlaces
  • Resumen
    • Although the traditional recurrent neural network (RNN) model can cover the time information of the whole sentencetheoretically, the gradient is dominated by the short-term gradient, and the long-term gradient is very small, which makes itdifficult for the model to learn the long-distance information, and thus the effect of RNN on long text sentence recognitionis poor. The long short-term memory network (LSTM) introduces the gate mechanism, especially the forgetting gate,which improves the disappearance of the gradient of RNN. Therefore, LSTM can store long text information and removeor increase the ability of information interaction by adding gate structure, which has natural advantages for long textprocessing. Based on the word vector matrix of GloVe model, on the open-source comment sentiment140 data set, weuse the TensorFlow framework to construct the LSTM neural network and divide the data into the training set and test setbased on the ratio of 4:1, design and implement the sentiment analysis published by Twitter users based on LSTM model,and then propose the bidirectional LSTM (Bi-LSTM) sentiment analysis method. The experimental results show that theaccuracy of bidirectional LSTM is higher than that of unidirectional LSTM in sentiment analysis


Fundación Dialnet

Dialnet Plus

  • Más información sobre Dialnet Plus

Opciones de compartir

Opciones de entorno