Sentiment Analysis of Chinese Commodity Reviews Based on Deep Learning

DOI

10.2991/assehr.k.200306.071How to use a DOI?

Keywords

sentiment analysis, deep learning, Chinese, LSTM, RNN

Abstract

Recent development of the Internet led to the emergence of product reviews with strong emotions on the e-commerce shopping platform. These reviews have become the main channel for people to know about the products. Sentiment analysis, a branch of natural language processing (NLP), is used to evaluate the emotion type described in the text. The establishment of individual emotional marker model allows us to identify the emotional characteristics of sentences based on the deep learning framework, thus obtaining accurate result of sentiment analysis. Results from Tensorflow deep learning framework, RNN and LSTM models are analyzed and compared, showing that the LSTM model has a better performance in the experiment as a guidance for the optimization of related sentiment analysis model.

Copyright

© 2020, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zifan Zhang
PY  - 2020
DA  - 2020/03/12
TI  - Sentiment Analysis of Chinese Commodity Reviews Based on Deep Learning
BT  - Proceedings of the International Conference on Modern Educational Technology and Innovation and Entrepreneurship (ICMETIE 2020)
PB  - Atlantis Press
SP  - 22
EP  - 28
SN  - 2352-5398
UR  - https://doi.org/10.2991/assehr.k.200306.071
DO  - 10.2991/assehr.k.200306.071
ID  - Zhang2020
ER  -