Emotional Analysis of Jingdong Commodity Review based on Deep Learning

DOI

10.2991/iccia-19.2019.6How to use a DOI?

Keywords

deep learning; commodity review sentiment analysis; recurrent neural network; Attention mechanism; AT-LSTM model.

Abstract

Jingdong commodity sentiment analysis aims to find out the e-commerce users' attitudes towards the products and the emotional orientation of the evaluation, helping other users to make correct decisions and effectively shape the quality portrait of the products. This paper proposes a subject-oriented AT-LSTM model method for traditional cyclic neural networks. The model is characterized by combining the Attention mechanism on the traditional LSTM model, highlighting the influence of the key input on the output through the Attention layer, and identifying the subject of the input phrase through the subject recognition algorithm, and then combine the phrase subject and the LSTM hidden layer result through the Attention mechanism. The experimental results show that the proposed method can obtain higher classification accuracy and save the workload of manual labeling.

Copyright

© 2019, 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  - Kang Xu
AU  - Ruichun Hou
AU  - Xiangqian Ding
AU  - Ye Tao
AU  - Zhifang Xu
PY  - 2019/07
DA  - 2019/07
TI  - Emotional Analysis of Jingdong Commodity Review based on Deep Learning
BT  - Proceedings of the 3rd International Conference on Computer Engineering, Information Science & Application Technology (ICCIA 2019)
PB  - Atlantis Press
SP  - 32
EP  - 41
SN  - 2352-538X
UR  - https://doi.org/10.2991/iccia-19.2019.6
DO  - 10.2991/iccia-19.2019.6
ID  - Xu2019/07
ER  -