Arabic Language Sentiment Analysis using Bidirectional Long Short Term Memory

Abstract

The amount of data generated in the digital era is huge since the super growth of social networks. Sentiment analysis (SA) seeks to extract opinions from a text and determine the polarity (positive, negative, or neutral). SA is widely used to refer to English. The topic of this study is SA in the Arabic language. There is an amalgamation between Word2Vec and Bidirectional Long-Short Time Memory (BLSTM) used in this paper. Firstly, words in reviews are transferred into their corresponding vectors with word representation models. Secondly, the sequence of words in the sentences passes as input to BLSTM. BLSTM not only captures long-range information and solves the gradient attenuation problem, but it also better represents the future semantics of the word sequence. The polarity was calculated using Word2Vec representation models, which rely on meaning and context. A BLSTM-based deep learning (DL) architecture is proposed. The result shows that the BLSTM Model Architecture surpasses ML, CNN, and LSTM Architectures with a maximum accuracy of 94.88 percent.