Integrated bidirectional LSTM–CNN model for customers reviews classification

Document Type : Original Article

Authors

1 computer engineering , MTC

2 Computer Engineering ,MTC

3 Computer Engineering , MTC

Abstract

The tremendous increase of Internet users and various social media
platforms provide a massive amount of data. Companies are seeking
an automated method to assess their customers' satisfaction with their
products. Collecting and analyzing opinions and customers' feedback
from social media rely on what so called sentiment classification. Several
types of research are carried out to investigate opinions in English.
As the Arabic language analysis faces many numerous challenges
and problems. In our current research, two powerful hybrid deep
learning models (CNN-LSTM) and (CNN- BILSTM) are represented.
Bidirectional LSTMs are an expansion of conventional LSTMs that
can make substantial improvements in sequence classification tasks
and identify the most valuable features, CNN is applied. Various data
preparation processes are performed, and two regular deep learning
models (CNN, LSTM) are implemented to conduct a series of
experiments. Experimental results show that the two proposed models
have superior performance compared to baselines deep learning models
(CNN, LSTM). Furthermore, the (CNN-BI-LSTM) model exceeds the
hybrid (CNN-LSTM) model in terms of achieving the highest efficiency.

Keywords

Main Subjects

Files

Share

How to cite

Statistics