Welcome to the InfoSci Platform
Reference Hub2
Microblog Sentiment Analysis Using User Similarity and Interaction-Based Social Relations

Microblog Sentiment Analysis Using User Similarity and Interaction-Based Social Relations

Chuanmin Mi, Xiaoyan Ruan, Lin Xiao
Copyright: © 2020 |Volume: 17 |Issue: 3 |Pages: 17
ISSN: 1545-7362|EISSN: 1546-5004|EISBN13: 9781799804918|DOI: 10.4018/IJWSR.2020070103
Cite Article Cite Article

MLA

Mi, Chuanmin, et al. "Microblog Sentiment Analysis Using User Similarity and Interaction-Based Social Relations." IJWSR vol.17, no.3 2020: pp.39-55. http://doi.org/10.4018/IJWSR.2020070103

APA

Mi, C., Ruan, X., & Xiao, L. (2020). Microblog Sentiment Analysis Using User Similarity and Interaction-Based Social Relations. International Journal of Web Services Research (IJWSR), 17(3), 39-55. http://doi.org/10.4018/IJWSR.2020070103

Chicago

Mi, Chuanmin, Xiaoyan Ruan, and Lin Xiao. "Microblog Sentiment Analysis Using User Similarity and Interaction-Based Social Relations," International Journal of Web Services Research (IJWSR) 17, no.3: 39-55. http://doi.org/10.4018/IJWSR.2020070103

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

With the rapid development of information technology, microblog sentiment analysis (MSA) has become a popular research topic extensively examined in the literature. Microblogging messages are usually short, unstructured, contain less information, creating a significant challenge for the application of traditional content-based methods. In this study, the authors propose a novel method, MSA-USSR, in which user similarity information and interaction-based social relations information are combined to build sentiment relationships between microblogging data. They make use of these microblog–microblog sentiment relations to train the sentiment polarity classification classifier. Two Sina-Weibo datasets were utilized to verify the proposed model. The experimental results show that the proposed method has a better sentiment classification accuracy and F1-score than the content-based support vector machine (SVM) method and the state-of-the-art supervised model known as SANT.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.