Research Article
Sentiment Prediction for User Comments on Home Appliances Products
@INPROCEEDINGS{10.4108/eai.27-8-2020.2285191, author={Ye Tao and Cao Shi and Canhui Xu and Ruichun Hou and Zhifang Xu}, title={Sentiment Prediction for User Comments on Home Appliances Products}, proceedings={Proceedings of the 13th EAI International Conference on Mobile Multimedia Communications, Mobimedia 2020, 27-28 August 2020, Cyberspace}, publisher={EAI}, proceedings_a={MOBIMEDIA}, year={2020}, month={11}, keywords={sentiment analysis product review continuous vector model}, doi={10.4108/eai.27-8-2020.2285191} }- Ye Tao
Cao Shi
Canhui Xu
Ruichun Hou
Zhifang Xu
Year: 2020
Sentiment Prediction for User Comments on Home Appliances Products
MOBIMEDIA
EAI
DOI: 10.4108/eai.27-8-2020.2285191
Abstract
Subjective information in products reviews play vital role in home appliances manufacturing industry. Generally, the comments are trusted worthy since we assume the customers will not make false ones. But in fact, there are cases that ratings and comments are not matched for some products. This paper proposed an approach to detect improper ratings by classifying and predicting the corresponding sentiment expressions in text reviews. To evaluate the effectiveness of the proposed method, we conducted experiments on a dataset which consists of customer reviews in 14 models of home appliances made by Haier. Results show that the sentiment polarity of the reviews can be predicted accurately, and the proposed method can be applied to detect and prevent a product from false rating.