Affiliations: [a] Department of Computer Science and Engineering, R.M.K College of Engineering and Technology, Anna University, Tamil Nadu, India
| [b] Department of Computer Science, Rajiv Gandhi National Institute of Youth Development (RGNIYD), Ministry of Youth Affairs & Sports, Government of India, Sriperumbudur, Tamil Nadu, India
Correspondence:
[*]
Corresponding author. Srividhya Lakshmi Ramaswamy, Department of Computer Science and Engineering, R.M.K College of Engineering and Technology, Anna University, Tamil Nadu, India. E-mail: srividhya.lakshmi89@gmail.com.
Abstract: The deep learning revolution in the current decade has transformed the artificial intelligence industry. Eventually, deep learning techniques have become essential for many computational modeling tasks. Nevertheless, deep neural models provide a high degree of automation for natural language processing (NLP) applications. Deep neural models are extensively used to decode public reviews subjective to specific products, services, and other social activities. Further, to improve sentiment classification accuracy, several neural architectures have been developed. Convolutional neural networks (CNN) and Long-short term memory (LSTM) are the popular deep models employed in ensemble architectures for sentiment classification tasks. This review article extensively compares the competence of CNN and LSTM-based ensemble models to improve the sentiment accuracy for online review datasets. Further, this article also provides an empirical study on various ensemble models concerning the position of LSTM and CNN for efficient sentiment classification. This empirical study provides deep learning researchers with insights into building effective multilayer LSTM and CNN models for many sentiment analysis tasks.
