Leveraging Arabic sentiment classification using an enhanced CNN-LSTM approach and effective Arabic text preparation

The high variety in the forms of Arabic words creates significant complexity related challenges Natural Language Processing (NLP) tasks for text. These can be dealt with by using different techniques semantic representation, such as word embedding methods. In addition, approaches reducing diversity morphologies also employed, example appropriate normalisation texts. Deep learning has proven to very popular solving NLP recent years well. This paper proposes an approach that combines Convolutional Neural Networks (CNNs) Long Short-Term Memory (LSTM) networks improve sentiment classification, excluding max-pooling layer from CNN. reduces length generated feature vectors after convolving filters on input data. As such, LSTM will receive well-captured maps. investigated effective preparing and representing text features order increase accuracy classification.