Comment Compass: An Approach to Analyze YouTube Comments through Web Scraping, Sentiment Analysis, and Generative AI for Actionable Insights

In this paper, we introduce “Comment Compass,” a novel system designed to revolutionize the analysis of YouTube video comments by content creators. The hypothesis driving this research is that integrating web scraping, sentiment analysis, and generative AI can provide content creators with deeper insights into their audience's sentiments and perspectives, thereby enhancing content strategy and engagement. Methodologically, “Comment Compass” employs Python-based web scraping to extract comments from YouTube videos. Sentiment analysis is conducted using the SentimentIntensityAnalyzer from the Natural Language Toolkit (NLTK) library, which produces a pie chart depicting the distribution of positive, negative, and neutral comments. Additionally, the system leverages Generative models to generate further insights from the comments, such as future content ideas, criticisms, and inquiries. Our results indicate that “Comment Compass” offers content creators actionable insights that can significantly optimize content strategies for better audience engagement and impact. This work demonstrates the substantial potential of combining web scraping, sentiment analysis, and generative AI, contributing valuable knowledge to these fields. The findings are contextualized within existing literature, underscoring the innovative contributions of this research.