Social Media Engagement Analysis

Author: Jorge Yamunaque
Role: Data Analyst / Entrepreneur
Tools: Python, Pandas, Seaborn, Matplotlib
Environment: Jupyter Notebook (iPad / a-Shell)

---

Project Overview

This project analyzes social media engagement data using Python. The goal is to explore how user interaction (measured by likes) varies across different content categories over a given period of time.

The dataset used in this project was randomly generated to simulate real-world social media engagement patterns and to demonstrate data analysis, visualization, and interpretation skills.

---

What This Project Demonstrates

• Data generation and structuring using Python
• Loading and cleaning data with Pandas
• Exploratory Data Analysis (EDA)
• Statistical summaries and interpretation
• Data visualization using Seaborn and Matplotlib
• Clear analytical reasoning and insights

---

Dataset Description

The dataset contains the following fields:

• Date: Date of the post
• topics: Category of the social media content
• likes: Number of likes received by the post

Each row represents a simulated social media post.

---

Steps Performed

1. Generated random social media engagement data
2. Loaded the data into a Pandas DataFrame
3. Cleaned the data by:
   • Removing null values
   • Removing duplicate records
4. Explored the data using:
   • head()
   • info()
   • describe()
5. Visualized engagement patterns using:
   • Histogram of likes distribution
   • Boxplot of likes by category
6. Performed statistical analysis:
   • Overall mean of likes
   • Mean likes per category

---

Key Insights

• User engagement varies significantly by content category
• Some categories show consistent engagement, while others exhibit high variability and occasional viral behavior
• Engagement distribution is broad, indicating diverse user interests
• Category choice plays an important role in interaction outcomes

---

How to Run the Project

1. Open the Jupyter Notebook (.ipynb file)
2. Run all cells from top to bottom
3. Visualizations will be generated and saved as image files
4. Statistical outputs will be printed in the notebook

Required Python libraries:

• pandas
• numpy
• matplotlib
• seaborn

---

Why This Project Matters

This project demonstrates practical data analysis skills that are directly applicable to real-world business and marketing scenarios, including performance analysis, user behavior understanding, and data-driven decision making.

---

Contact

GitHub: https://github.com/JorgePulp LinkedIn: http://linkedin.com/in/jorgeyamunaquheredia