Published Paper Details:

This research introduces a sophisticated sentiment analysis framework tailored specifically for YouTube comments, providing valuable insights for content creators and stakeholders. It comprises four pivotal components: sentiment classification, visualization of sentiment distribution, temporal sentiment analysis, and automated email summaries. The sentiment analysis module employs a Random Forest algorithm (chosen for its adaptability to high-dimensional data and resistance to overfitting) or Naive Baye's (Naive Bayes classifiers have been widely applied for their simplicity and efficiency in handling high-dimensional data, making them a popular choice for sentiment analysis tasks). This enables the system to categorize comments into positive, negative, and neutral sentiments. Additionally, an intuitive visualization feature employs charts and graphs to represent sentiment distribution, allowing users to interpret trends within the comment section. The system also conducts temporal analysis, examining how sentiments change over time about video upload and comment submission dates. This provides content creators with a nuanced understanding of audience feedback dynamics. A key feature is the automated email functionality, streamlining the distribution of sentiment analysis summaries to users. This ensures stakeholders receive timely, actionable insights, enhancing their responsiveness to viewer feedback. By combining these elements, this research introduces a comprehensive sentiment analysis solution tailored for YouTube comments. The framework not only categorizes sentiments but also equips content creators with tools to visualize trends and receive timely summaries, offering a multifaceted approach to deciphering audience feedback.