Aspect Identification of Sentiment Sentences Using A Clustering Algorithm

This paper proposes an aspect identification method for sentiment sentences in review documents that acquires new training data from non-tagged data by using the clustering approach.

Abstract

Reviews contain aspect information of a product, such as "image quality" and "usability" of a camera. In this paper, we propose an aspect identification method for sentiment sentences in review documents. Machine learning methods usually require a large amount of training data for generating a classifier with high accuracy. However, preparing training data by hand is costly. To solve this problem, we apply a clustering approach to the aspect identification method. Our system acquires new training data from non-tagged data by using the clustering approach. As compared with a baseline method, which does not use the acquisition approach, our method obtained high accuracy.