The goal of this task is to analyze and visualize sentiment patterns in social media data to understand public opinion and attitudes toward specific topics or brands. This analysis helps in identifying trends, key sentiments, and engagement metrics across platforms like Instagram, Twitter, and Facebook.
Power BI: For data visualization and analysis of sentiment trends, platforms, and user engagement.
Kaggle Dataset: The sentiment analysis was performed using the Twitter Entity Sentiment Analysis dataset, which you can access here.
Hashtags Sentiment Analysis: Visualized the top 10 hashtags used across platforms and their associated sentiments. Sentiment by Platform: Analyzed how sentiment varies by platform (Instagram, Twitter, Facebook). Top Sentiments by Users: Identified the top six sentiments, such as Zest, Wonder, Winter Magic, and others. Sentiment by Countries: Mapped the countries that show the most engagement across various sentiments. Engagement Metrics: Measured the count of sentiments, user engagement (likes, retweets), and platform-specific retweets. Visuals
Sentiment distribution by platform: Compare Instagram, Twitter, and Facebook. Hashtag analysis: Popular hashtags and the corresponding sentiments. Country-specific sentiment: Sentiments originating from specific countries like the USA, Greece, Japan, etc. Engagement by Hour: Shows when certain sentiments are most active during the day. Retweets and likes by sentiment: Detailed analysis of the engagement metrics for each sentiment. Sample Visuals
The dashboard allows filtering by year and month, giving insights into sentiment trends over time. You can also filter by platform to see how each one contributes to overall sentiment and engagement.
This project provides a comprehensive analysis of public opinion and brand sentiment using social media data, visualized through Power BI. The results can be utilized by marketers, brand strategists, and social media managers to understand user engagement and adjust strategies accordingly.
