A Review Towards Deep Learning for Sentiment Analysis

Abstract

Due to the advent of Web 2.0 and Internet boom, social media is essential to generate vast amount of data that can be analyzed for various purposes. For instance, we can use the vast amount of data for sentiment analysis and opinion mining. Nowadays, it is prevalent to find out the sentiments of the customers regarding products or services offered specially to increase the sales with proper actions taken from the predictions. In short, it is to determine how people feel about a specific topic. Although sentiment analysis and opinion mining are slightly different, there are often used interchangeably under the text mining and natural language processing fields. Two approaches for the sentiment analysis: lexicon analysis or machine learning. For the machine learning approaches, there are supervised, unsupervised and semi-supervised learning approaches. Deep learning is a new era of machine learning techniques that overcome the weaknesses of earlier machine learning techniques that is Artificial Neural Network (ANN) and Deep Neural Network (DNN). DNN has Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN). In this paper, the deep learning techniques will be surveyed to discuss the importance from moving towards from machine learning to deep learning for the classification.