Hybrid convolutional bidirectional recurrent neural network based sentiment analysis on movie reviews. (20th September 2020)

• Record Type: Journal Article
• Authors: Soubraylu, Sivakumar; Rajalakshmi, Ratnavel
• Other Names: Li Ying guestEditor.; Shyamasundar R.K. guestEditor.; Wang Xinheng guestEditor.
• Is Part Of: Computational intelligence. Volume 37:Number 2(2021)
• Page Start: 735
• Page End: 757
• Publication Date: 2020-09-20
• Subjects: bidirectional gated recurrent unit (BGRU) -- convolutional bidirectional recurrent neural network (CBRNN) -- sentiment analysis (SA); Artificial intelligence -- Periodicals; Computational linguistics -- Periodicals; 006.3
• DOI: 10.1111/coin.12400
• Languages: English
• ISSNs: 0824-7935

Abstract

Abstract: Sentiment analysis is the process of extracting the opinions of customers from online reviews. In general, customers express their reviews in natural language. It becomes a complex task when applying sentiment analysis on those reviews. In earlier stages, word‐level features with various feature weighting methods such as Bag of Words, TF‐IDF, and Word2Vec were applied for sentiment analysis and deep learning networks are not explored much. We considered phrase level and sentence level features instead of applying word‐level features for sentiment analysis and also enhanced by applying various deep learning techniques. In this article, we have proposed a hybrid convolutional bidirectional recurrent neural network model (CBRNN) by combining two‐layer convolutional neural network (CNN) with a bidirectional gated recurrent unit (BGRU). In the proposed CBRNN model, the CNN layer extracts the rich set of phrase‐level features and BGRU captures the chronological features through long term dependency in a multi‐layered sentence. The proposed approach was evaluated on two benchmark datasets and compared with various baselines. The experimental results show that the proposed hybrid model provides better results than any other models with an F1 score of 87.62% and 77.4% on IMDB and Polarity datasets, respectively. Our CBRNN model outperforms the state of the art by 2%‐4% on these two datasets. It is also observed that, the time taken for training is slightly higher than the existing approaches with the substantial improvement in the performance.