Attention-Based Convolution Bidirectional Recurrent Neural Network for Sentiment Analysis

A customer conveys their opinion in natural language about an entity. Applying sentiment analysis to those reviews is a very complex task. The significant terms that influence the polarity of a review are not examined. The terms that have contextual meaning are not recognized and are present across multiple sentences in a review. To address the above two issues, the authors have proposed an attention-based convolution bi-directional recurrent neural network (ACBRNN). In this model, two convolution layer captures phrase-level feature while self-attention in the middle assigns high weight to the significant terms, and bi-directional GRU performs a conceptual scanning of review through forward and backward direction. The authors have conducted four different experiments (i.e., unidirectional, bidirectional, hybrid, and proposed model) on IMDB dataset to show the significance of the proposed model. The proposed model has obtained an F-1 score of 87.94% on IMDB dataset, which is 5.41% higher than CNN. Thus, the proposed architecture performs well compared with all other baseline models.