A simulated social media data pipeline that generates, processes, and visualizes user interaction data. Includes sentiment analysis with TextBlob and data visualization with Matplotlib.
Academic project — Data Analysis module, L3 Computer Science @ UVSQ
- Simulated social network data generation (users, posts, comments, likes)
- Object-oriented pipeline architecture (OOP)
- Sentiment analysis on text content using TextBlob (polarity and subjectivity scoring)
- Data cleaning and transformation with Pandas
- Statistical visualizations: engagement metrics, sentiment distribution, activity trends
- Jupyter Notebook for interactive exploration
Data Generation → Cleaning & Transformation → Sentiment Analysis → Visualization
(OOP) (Pandas) (TextBlob) (Matplotlib)
| Component | Technology |
|---|---|
| Language | Python |
| Data processing | Pandas |
| NLP | TextBlob |
| Visualization | Matplotlib |
| Notebook | Jupyter |
| Paradigm | Object-Oriented Programming |
git clone https://github.com/AmZzPYJS/InPoDa-Social-Data-Analysis.git
cd InPoDa-Social-Data-Analysis
pip install -r requirements.txt
jupyter notebook- Designing a data pipeline from generation to visualization
- Applying OOP principles to structure a data project (classes for Users, Posts, Interactions)
- Using TextBlob for basic NLP tasks (sentiment polarity, subjectivity)
- Creating meaningful visualizations that tell a story from raw data
- Working with Jupyter Notebooks for exploratory data analysis
MIT