A comprehensive data visualization platform for analyzing sentiment patterns across multiple dimensions using interactive dashboards built with Streamlit and Plotly.

1. 🌍 GeoSentiment Map Explorer

   • Interactive global sentiment mapping
   • Time-series analysis with sliders
   • Location-based sentiment patterns
   • Country and city-level insights

2. 🎯 Topic & Hashtag Sentiment Radar

   • Radar charts for hashtag sentiment comparison
   • Word clouds by sentiment categories
   • Hashtag trend analysis over time
   • Topic performance metrics

3. ⏰ Temporal Emotion Evolution Dashboard

   • Weekday vs Hour sentiment heatmaps
   • Circular 24-hour emotion wheels
   • Daily sentiment evolution charts
   • Emotion distribution over time

4. 🌟 Influencer Impact Visualizer

   • Bubble charts: followers vs sentiment vs engagement
   • Network graphs showing influence relationships
   • User clustering analysis (K-means)
   • Influencer performance rankings

5. 📱 Device & Language Bias Dashboard

   • Sankey diagrams: Language → Sentiment → Device flow
   • Statistical bias detection
   • Cross-platform sentiment analysis
   • Language sentiment profiling

• Interactive Visualizations: 15+ chart types including radar, Sankey, network graphs, heatmaps
• Real-time Filtering: Date ranges, devices, languages, user types
• Statistical Analysis: Bias detection, correlation matrices, clustering
• Rich Dataset: 10,000+ synthetic social media records
• Export Capabilities: Download filtered data as CSV
• Responsive Design: Works on desktop and mobile

Python 3.7+

# Clone the repository
cd sentiment-dashboard

# Create virtual environment
python3 -m venv venv
source venv/bin/activate  # On Windows: venv\\Scripts\\activate

# Install dependencies
pip install -r requirements.txt

# Generate sample data
python utils/data_generator.py

streamlit run app.py

The application will open in your browser at http://localhost:8501

sentiment-dashboard/
├── app.py                          # Main Streamlit application
├── requirements.txt                # Python dependencies
├── README.md                       # This file
├── data/
│   └── sentiment_data.csv         # Generated dataset
├── dashboards/
│   ├── __init__.py
│   ├── geo_sentiment_map.py       # Geographic analysis
│   ├── hashtag_sentiment_radar.py # Topic & hashtag analysis
│   ├── temporal_emotion_dashboard.py # Time-based analysis
│   ├── influencer_impact_dashboard.py # Influence network analysis
│   └── device_language_bias_dashboard.py # Platform bias analysis
└── utils/
    └── data_generator.py          # Synthetic data generation

The synthetic dataset includes:

• Temporal: Timestamps, weekdays, hours
• Geographic: Cities, countries, coordinates (12 locations)
• Linguistic: 10 languages with realistic distributions
• Technical: 5 device types (iPhone, Android, Web, etc.)
• Social: Follower counts, verification status, engagement metrics
• Content: Hashtags, sentiment scores, emotion labels

• Frontend: Streamlit (Interactive web interface)
• Visualization: Plotly (Interactive charts)
• Data Processing: Pandas, NumPy
• Machine Learning: Scikit-learn (Clustering)
• Network Analysis: NetworkX
• Text Processing: WordCloud, TextBlob
• Statistical Analysis: Custom bias detection algorithms

• Geographic: Scatter maps, choropleth maps
• Network: Force-directed graphs, node-link diagrams
• Temporal: Heatmaps, time series, circular plots
• Statistical: Radar charts, correlation matrices, bubble charts
• Flow: Sankey diagrams
• Text: Word clouds
• Clustering: 3D scatter plots

• Social Media Analytics: Understand sentiment patterns across platforms
• Brand Monitoring: Track sentiment by geography and demographics
• Content Strategy: Optimize posting times and hashtag usage
• Bias Detection: Identify platform or language-specific sentiment biases
• Influence Analysis: Understand how different user types affect sentiment
• Academic Research: Study sentiment patterns in social data

1. Create a new Python file in dashboards/
2. Implement a main() function
3. Add import to app.py
4. Add navigation option

• Edit utils/data_generator.py to change dataset characteristics
• Update CSV file path in dashboard modules
• Adjust date ranges and filters as needed

• Handles 10,000+ records smoothly
• Interactive filtering without page reloads
• Optimized aggregations and memory usage
• Responsive design for various screen sizes

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests if applicable
5. Submit a pull request

This project is open source and available under the MIT License.

• Streamlit - For the amazing web app framework
• Plotly - For interactive visualizations
• OpenStreetMap - For map data
• Community - For inspiration and feedback

For questions, suggestions, or collaboration:

• Create an issue on GitHub
• Contribute to the discussion

Built with ❤️ for data visualization enthusiasts