SENTIMENT CLASSIFICATION OF E-COMMERCE REVIEWS BASED ON BERT-CNN

CUNHAO CHAI

School of Engineering, Hangzhou Normal University, Hangzhou, Zhejiang, 310018, China.

LU LI

School of Engineering, Hangzhou Normal University, Hangzhou, Zhejiang, 310018, China.

TENGZE MAO

School of Engineering, Hangzhou Normal University, Hangzhou, Zhejiang, 310018, China.

DIAN WU

Qianjiang College, Hangzhou Normal University, Hangzhou, Zhejiang, 310018, China.

LIDONG WANG *

School of Engineering, Hangzhou Normal University, Hangzhou, Zhejiang, 310018, China.

*Author to whom correspondence should be addressed.


Abstract

Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) were used to handle natural language tasks in early days, but the Transformer model changed that. The Bidirectional Encoder Representations from Transformers (BERT) model is another optimization based on the Transformer model, which directly makes the performance of the NLP model reach an unprecedented height. In order to distinguish the emotion classification model with the best processing effect in the field of e-commerce reviews, the BERT model is fine-tuned based on the mobile e-commerce review data, and then input to another deep learning models(such as CNN,RNN) as embedding. Finally, we compare the training effect of several current deep learning models, such as BERT, BERT-RNN and BERT-CNN. Experimental results show that the BERT-CNN model performs best in the binary classification of e-commerce review text sentiment.

Keywords: Sentiment classification, BERT, BERT-CNN, TextCNN, word embedding


How to Cite

CHAI, C., LI, L., MAO, T., WU, D., & WANG, L. (2022). SENTIMENT CLASSIFICATION OF E-COMMERCE REVIEWS BASED ON BERT-CNN. Asian Journal of Mathematics and Computer Research, 29(3), 40–49. https://doi.org/10.56557/ajomcor/2022/v29i37961

Downloads

Download data is not yet available.

References

Wang L, Zhang Y, Hu K. FEUI: Fusion embedding for user identification across social networks [J]. Applied Intelligence. 2022;52(7):8209-8225.

Wang L, Zhang Y, Xu X. A novel group detection method for finding related Chinese herbs [J]. J. Inf. Sci. Eng. 2015;31(4):1387-1411.

Wang L, Zhang Y, Zhang Y, et al. Prescription function prediction using topic model and multilabel classifiers [J]. Evidence-Based Complementary and Alternative Medicine, 2017, 2017.

Wang L, Zhang Y, Yuan J, et al. FEBDNN: Fusion embedding-based deep neural network for user retweeting behavior prediction on social networks [J]. Neural Computing and Applications. 2022;1-17.

Kalchbrenner N, Grefenstette E, Blunsom P. A convolutional neural network for modelling sentences [J]. arXiv preprint arXiv:1404.2188, 2014.

Lai S, Xu L, Liu K, et al. Recurrent convolutional neural networks for text classification[C]. Twenty-Ninth AAAI Conference on Artificial Intelligence; 2015.

BERT:Pre-training of deep bidirectional transformers for language understanding [EB/OL].[2021-06-24].

Available:https://arxiv. org/pdf/1810.04805.pdf

Liu B, Hsu W, Ma Y. Integrating classification and association rule mining[C]. Kdd. 1998;98:80-86.

Hu Chaoju, Zhao Xiaowei. Sentiment analysis based on word vector technology and hybrid neural networks [J]. Computer Application Research. 2018,35(12):3556.

Chen Geheng, Text sentiment analysis based on polarity shift and bidirectional LSTM[J]. Information Technology. 2018(2):149.

Zou Borong, Wang Yichen, Wang Weidong, Hou Qinghua, Wu Huibin. Text sentiment classification based on dual-channel composite model of attention mechanism [J]. Journal of Henan Polytechnic University (Natural Science Edition). 2022;41(06):155-162.

Safaya A, Abdullatif M, Yuret D. Kuisail at semeval-2020 task 12: Bert-cnn for offensive speech identification in social media[C]//Proceedings of the Fourteenth Workshop on Semantic Evaluation. 2020; 2054-2059.

Wang L, Hu K, Zhang Y, et al. Factor graph model based user profile matching across social networks [J]. IEEE Access. 2019;7:152429-152442.