Lexicon Based Chinese Language Sentiment Analysis Method

Jinyan Chen1, Susanne Becken2 and Bela Stantic3

  1. Griffith Institute for Tourism
    Griffith University, Queensland, Australia
  2. Griffith Institute for Tourism
    Griffith University, Queensland, Australia
  3. School of Information and Communication Technology
    Griffith University, Queensland, Australia


The growing number of social media users and vast volume of posts could provide valuable information about the sentiment toward different locations, services as well as people. Recent advances in Big Data analytics and natural language processing often means to automatically calculate sentiment in these posts. Sentiment analysis is challenging and computationally demanding task due to the volume of data, misspelling, emoticons as well as abbreviations. While significant work was directed toward the sentiment analysis of English text there is limited attention in literature toward the sentiment analytic of Chinese language. In this work we propose method to identify the sentiment in Chinese social media posts and to test our method we rely on posts sent by visitors of Great Barrier Reef by users of most popular Chinese social media platform Sina Weibo. We elaborate process of capturing of weibo posts, describe a creation of lexicon as well as develop and explain algorithm for sentiment calculation. In case study, related to sentiment toward the different GBR destinations, we demonstrate that the proposed method is effective in obtaining the information and is suitable to monitor visitors’ opinion.

Key words

Sentiment Analysis, Social Media, Natural Language Processing

Digital Object Identifier (DOI)


Publication information

Volume 16, Issue 2 (June 2019)
Year of Publication: 2019
ISSN: 1820-0214 (Print) 2406-1018 (Online)
Publisher: ComSIS Consortium

Full text

DownloadAvailable in PDF
Portable Document Format

How to cite

Chen, J., Becken, S., Stantic, B.: Lexicon Based Chinese Language Sentiment Analysis Method. Computer Science and Information Systems, Vol. 16, No. 2, 639-655. (2019), https://doi.org/10.2298/CSIS123456789X