Analyzing Political Figures in Real-Time: Leveraging YouTube Metadata for Sentiment Analysis

TL;DR

This paper presents a system for real-time sentiment analysis of political figures using YouTube video metadata, employing big data tools and deep learning to classify sentiments and visualize results.

Contribution

It introduces a novel sentiment analysis system leveraging YouTube metadata with an integrated big data and deep learning framework for political sentiment monitoring.

Findings

Effective classification of positive and negative sentiments

Real-time sentiment visualization dashboard created

System demonstrates scalability with big data tools

Abstract

Sentiment analysis using big data from YouTube videos metadata can be conducted to analyze public opinions on various political figures who represent political parties. This is possible because YouTube has become one of the platforms for people to express themselves, including their opinions on various political figures. The resulting sentiment analysis can be useful for political executives to gain an understanding of public sentiment and develop appropriate and effective political strategies. This study aimed to build a sentiment analysis system leveraging YouTube videos metadata. The sentiment analysis system was built using Apache Kafka, Apache PySpark, and Hadoop for big data handling; TensorFlow for deep learning handling; and FastAPI for deployment on the server. The YouTube videos metadata used in this study is the video description. The sentiment analysis model was built using LSTM algorithm and produces two types of sentiments: positive and negative sentiments. The sentiment analysis results are then visualized in the form a simple web-based dashboard.