Abstract
Online reviews are acknowledged as an important source of product information when customers make purchasing decisions. However, in the era of information overload, product review data on the Internet are too abundant and contain much irrelevant information. This makes it difficult for customers to find useful reviews. To solve this issue, some e-commerce websites provide keywords for product reviews, but these are generated beforehand and have the potential to distort customers' opinions of products. This paper presents an automatic keyword extraction method based on a bi-directional long short-memory (LSTM) recurrent neural network (RNN). The results of experiments conducted on product reviews obtain by data-crawling jd.com show that the proposed approach has a very high accuracy of keyword extraction. This can help reduce human annotation efforts in e-commerce. Copyright © 2017 IEEE.
Original language | English |
---|---|
Title of host publication | Proceedings of 2017 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2017 |
Place of Publication | USA |
Publisher | IEEE |
Pages | 2241-2245 |
ISBN (Electronic) | 9781538609484 |
DOIs | |
Publication status | Published - 2017 |
Citation
Wang, Y., & Zhang, J. (2017). Keyword extraction from online product reviews based on bi-directional LSTM recurrent neural network. In Proceedings of 2017 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2017 (pp. 2241-2245). IEEE. https://doi.org/10.1109/IEEM.2017.8290290Keywords
- Deep learning
- E-commerce
- Product design