Title: Sentiment classification of online Cantonese reviews by supervised machine learning approaches

Authors: Ziqiong Zhang, Qiang Ye, Yijun Li, Rob Law

Addresses: School of Management, Harbin Institute of Technology, Harbin, China. ' School of Management, Harbin Institute of Technology, Harbin, China. ' School of Management, Harbin Institute of Technology, Harbin, China. ' School of Hotel and Tourism Management, Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong SAR, China

Abstract: Cantonese is an important Chinese dialect spoken in some regions of Southern China. Local online users often represent their opinions and experiences with written Cantonese on the web. With two supervised machine learning approaches, this paper conducts a series of experiments to explore appropriate methods for automatic sentiment classification in the very noisy domain of online Cantonese-written reviews. Findings indicate that the support vector machine classifier based on a Mandarin Chinese word segmentation tool performs surprisingly well. The accuracy, precision and recall respectively for positive and negative reviews all reach above 85% when the training corpus contains 5,000 or more reviews.

Keywords: text mining; sentiment classification; online reviews; Cantonese; machine learning; supervised learning; support vector machines; SVM classifiers.

DOI: 10.1504/IJWET.2009.032254

International Journal of Web Engineering and Technology, 2009 Vol.5 No.4, pp.382 - 397

Published online: 18 Mar 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article