A novel BiGRUBiLSTM model for Multilevel Sentiment Analysis Using Deep Neural Network with BiGRU-BiLSTM

Islam, Md Shofiqul and Ngahzaifa, Ab. Ghani (2021) A novel BiGRUBiLSTM model for Multilevel Sentiment Analysis Using Deep Neural Network with BiGRU-BiLSTM. In: Recent Trends in Mechatronics Towards Industry 4.0: Selected Articles from iM3F 2020, Malaysia , 6 August 2020 , Universiti Malaysia Pahang (Virtual). pp. 403-414., 730. ISBN 978-981-33-4597-3

Pdf A novel BiGRUBiLSTM model for multilevel sentiment analysis using deep neural network with BiGRU- BiLSTM.pdf Restricted to Repository staff only Download (436kB) | Request a copy

Abstract

In multilevel sentiment classification task, there is a challenging task of limited coherence, contextual and semantic information. This paper proposes a new hybrid deep learning architecture for multilevel text sentiment classification with less training and simple network structure for better performance and can handle the implicit semantic information and contextual meaning of text. In this research the proposed hybrid deep neural network architecture made with Bidirectional Gated Recurrent Unit (BiGRU) and Bi-Directional Long Term Short Memory(BiLSTM) of Recurrent Neural Network (RNN) for multilevel text sentiment classification and this performs better with higher accuracy than other methods compared. This proposed method BiGRUBiLSTM model outperformed the traditional machine learning methods and the compared deep learning models with about average of 1% margin accuracy on different datasets.

Item Type:	Conference or Workshop Item (Lecture)
Uncontrolled Keywords:	GRU, Bi-GRU, BiLSTM, LSTM, Sentiment analysis, Text Classification, Machine Learning, Natural Language Processing.
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software
Faculty/Division:	Institute of Postgraduate Studies Faculty of Computing
Depositing User:	Miss. Ratna Wilis Haryati Mustapa
Date Deposited:	24 Jan 2022 07:52
Last Modified:	25 Jan 2022 03:18
URI:	http://umpir.ump.edu.my/id/eprint/33280
Download Statistic:	View Download Statistics

Actions (login required)

View Item