Effect Research of Aspects Extraction for Chinese Hotel Reviews Based on Machine Learning Method
Yan Zhao, Suyu Dong, Jin Tan Yang · International Journal of Smart Home · 2015
With the development of Web, there are more and more online reviews. These reviews have become the important information for people. Therefore, automatic analysis of online reviews has become the active research area in natural language processing and management sciences. Apart from the researches about document sentiment classification and sentence sentiment classification, there are an increasing number researches about aspect-based sentiment analysis. This paper tries to use machine learning to extract aspect from Chinese hotel reviews. Through a lot of experiments, we find that machine learning methods are suitable for the aspect extraction of Chinese reviews. This paper adopts different dimensions of features, feature representation methods and classifiers to analyze the integral effect of aspect extraction. The experiment result shows that ME is the best classifiers and presence is most suitable feature representation method for aspect extraction.