The research for effect of aspects extraction of Chinese commodity comments on supervised learning methods
Yan Zhao1, Suyu Dong1, Hua Yang2, Jing Yang 3
COMPUTER MODELLING & NEW TECHNOLOGIES 2014 18(12C) 1211-1218
1 College of Management, Inner Mongolia University of Technology, Huhhot, China;
2 College of Information Engineering, Inner Mongolia University of Technology, Huhhot, China;
3 College of Mechanical Engineering, Inner Mongolia University of Technology, Huhhot, China;
With the advent of Web 2.0, there are more and more websites for shopping. These websites often allow customers make comments of the commodity which they have purchased. Therefore, three is an increasing number of online reviews. More importantly, these reviews contain a mass of sentiment. The sentiment is meaningful for merchants and customers. This paper focuses on the extraction of aspects of online review of products. We will use Supervised Learning methods to extract aspects of online review of products. Through the experiment of this paper, we found that Machine Learning can be used for aspects extraction of Chinese online review of products. Using ME and presence character representation can achieve 85.6% accuracy.