An Improved Approach for Text Sentiment Classification Based on a Deep Neural Network via a Sentiment Attention Mechanism

Li Li,Liu Liu,Zhang Zhang

doi:10.3390/fi11040096

Abstract

Text sentiment analysis is an important but challenging task. Remarkable success has been achieved along with the wide application of deep learning methods, but deep learning methods dealing with text sentiment classification tasks cannot fully exploit sentiment linguistic knowledge, which hinders the development of text sentiment analysis. In this paper, we propose a sentiment-feature-enhanced deep neural network (SDNN) to address the problem by integrating sentiment linguistic knowledge into a deep neural network via a sentiment attention mechanism. Specifically, first we introduce a novel sentiment attention mechanism to help select the crucial sentiment-word-relevant context words by leveraging the sentiment lexicon in an attention mechanism, which bridges the gap between traditional sentiment linguistic knowledge and current popular deep learning methods. Second, we develop an improved deep neural network to extract sequential correlation information and text local features by combining bidirectional gated recurrent units with a convolutional neural network, which further enhances the ability of comprehensive text representation learning. With this design, the SDNN model can generate a powerful semantic representation of text to improve the performance of text sentiment classification tasks. Extensive experiments were conducted to evaluate the effectiveness of the proposed SDNN model on two real-world datasets with a binary-sentiment-label and a multi-sentiment-label. The experimental results demonstrated that the SDNN achieved substantially better performance than the strong competitors for text sentiment classification tasks.

Highlights

With the exponential growth of large collections of opinion-rich resources, sentiment classification [1] has been one of the most important tasks in natural language processing (NLP), which aims to automatically classify the sentiment polarity of a given text as negative, positive or more fine-grained classes
The traditional machine learning-based representation models train a sentiment classifier relying on sentiment linguistic knowledge such as bag-of-words and sentiment lexicon, where the sentiment polarity of text is largely determined to be positive if the number of positive words is larger than that of the negative ones
We mainly focus on integrating sentiment linguistic knowledge into the deep neural network to enhance the quality of text representation learning for sentiment classification task

Summary

Introduction

With the exponential growth of large collections of opinion-rich resources, sentiment classification [1] has been one of the most important tasks in natural language processing (NLP), which aims to automatically classify the sentiment polarity of a given text as negative, positive or more fine-grained classes. Mainstream representation models for text sentiment classification can be divided into two categories based on the knowledge and information they use: traditional machine learning-based representation models and current popular deep learning-based representation models. The traditional machine learning-based representation models train a sentiment classifier relying on sentiment linguistic knowledge such as bag-of-words and sentiment lexicon, where the sentiment polarity of text is largely determined to be positive if the number of positive words is larger than that of the negative ones. The current popular deep learning-based representation models utilize the deep neural network to learn the semantic information contained in text. We mainly focus on integrating sentiment linguistic knowledge into the deep neural network to enhance the quality of text representation learning for sentiment classification task

Objectives

Methods

Results