Enhancing Public Opinion Analysis on Weibo: An ANN-Based Approach for Unlabeled Sentiment Classification

Main Article Content

Chao Chen

Abstract

With the rapid growth of Internet usage, social platforms like Weibo play a critical role in public opinion formation and dissemination. However, the vast amount of unstructured and unlabeled data presents challenges in accurately gauging public sentiment, especially given the prevalence of misinformation and the evolving complexity of online expression. This study proposes an innovative sentiment analysis framework employing Artificial Neural Networks (ANN) to classify unlabeled Weibo comments effectively. By converting unlabeled data into labeled datasets, this approach overcomes traditional data limitations, expanding the dataset significantly to enhance model reliability and accuracy. The model enables more effective public opinion monitoring, providing governmental and organizational stakeholders with refined tools for public sentiment assessment, intervention planning, and policy decision-making.

Article Details

How to Cite
Chen, C. (2024). Enhancing Public Opinion Analysis on Weibo: An ANN-Based Approach for Unlabeled Sentiment Classification. Journal of Computer Science and Software Applications, 7(4), 19–24. Retrieved from https://mfacademia.org/index.php/jcssa/article/view/172
Section
Articles