Research on Sentiment Analysis of Chinese E-Commerce Comments Based on Deep Learning

Abstract

The analysis of emotional polarity of Chinese phrases in complex contexts has always been a problem in the field of machine learning. The emergence of Artificial Neural Networks has opened a window to solve this problem. Sentiment analysis has also become a hotspot in the research. This paper aims to solve this problem by introducing Attention mechanism to the Temporal Convolutional Nets (TCN) model. This paper chooses the Chinese commodity comment phrase on the E-commerce platform as the research object, to automatically analyse and judge the polarity (positive and negative) of each comment phrase. This paper optimized the design and constructed of the TCN Attention model, which made the TCN Attention model show superior performance in the area of sentiment analysis, and improved significantly compared with other models.