Sentiment Analysis based on User Tag for Traditional Chinese Medicine in Weibo

TL;DR

This paper presents a novel sentiment analysis approach for Traditional Chinese Medicine on Sina Weibo, using user tags for labeling and SVM for classification, achieving high accuracy in sentiment prediction.

Contribution

It introduces a new method for sentiment analysis in TCM domain on Sina Weibo, utilizing user tags for automatic labeling and classifier adjustment for improved accuracy.

Findings

F-measure of 97% achieved with the proposed method

First application of sentiment analysis to TCM on Sina Weibo

Effective automatic labeling based on user tags

Abstract

With the acceptance of Western culture and science, Traditional Chinese Medicine (TCM) has become a controversial issue in China. So, it's important to study the public's sentiment and opinion on TCM. The rapid development of online social network, such as twitter, make it convenient and efficient to sample hundreds of millions of people for the aforementioned sentiment study. To the best of our knowledge, the present work is the first attempt that applies sentiment analysis to the domain of TCM on Sina Weibo (a twitter-like microblogging service in China). In our work, firstly we collect tweets topic about TCM from Sina Weibo, and label the tweets as supporting TCM and opposing TCM automatically based on user tag. Then, a support vector machine classifier has been built to predict the sentiment of TCM tweets without labels. Finally, we present a method to adjust the classifier result. The performance of F-measure attained with our method is 97%.