Scholarlink

Social media platforms such as Twitter serve as powerful tools for real-time information dissemination and worldwide communication, shaping public opinions and providing a platform for diverse voices to be heard. The current study proposes methods to determine the trending hashtags on Twitter and then accomplish sentiment analysis on the hashtags. The investigation of trending hashtags is carried out through Naive Bayes, Gradient Boosting Decision Tree (GBDT), and Random Forest, while the sentiment analysis is carried out using the Vader sentiment analysis model. The experiment was conducted on a Twitter dataset collected over a period of six months for the year 2021. The experimental results show the efficiency of Random Forest algorithms over the other two methods in determining the trending hashtags.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Determining Twitter Trending Hashtags and Sentiments Associated via Naïve Bayes, GBDT, and Random Forest Approaches

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Tanvi Bisht,
  • Muskan Singh,
  • Shweta Singhal,
  • Uma Nirmal

摘要

Social media platforms such as Twitter serve as powerful tools for real-time information dissemination and worldwide communication, shaping public opinions and providing a platform for diverse voices to be heard. The current study proposes methods to determine the trending hashtags on Twitter and then accomplish sentiment analysis on the hashtags. The investigation of trending hashtags is carried out through Naive Bayes, Gradient Boosting Decision Tree (GBDT), and Random Forest, while the sentiment analysis is carried out using the Vader sentiment analysis model. The experiment was conducted on a Twitter dataset collected over a period of six months for the year 2021. The experimental results show the efficiency of Random Forest algorithms over the other two methods in determining the trending hashtags.