📊 Data Analysis in Social Media Sphere

🚀 A Case Study of a Startup Social Media Platform

For a surface brief, check out this site.

✍🏼 Tracking of all the files using git

All the files are tracked with Git to keep an eye on the changes every time a modification is made.DVC can be used for data tracking but the data isn't upgrading rather its a constant data so DVC isn't used in this projcet.

❓ Problem Statement

In the dynamic landscape of social media, the year 2023 presents a challenge and opportunity for innovation. With a staggering 4.8 billion social media users worldwide, constituting 59.9% of the global population and captivating 92% of all internet users, the realm of social media continues to evolve. Notably, there have been 150 million new social media users between April 2022 and April 2023, marking a 3.2% year-on-year increase.

Developing a social media platform in the current digital era is akin to a delicate dance on the cutting edge. The challenges are manifold:

1. Enhancing User Experience:
   • How can we elevate the user experience for existing users?
   • What strategies can be implemented to attract and retain new users amidst the competitive landscape?
2. Connecting Business and Data:
   • How do we effectively bridge the gap between business objectives and the vast data generated on the platform?
   • What insights can be derived from data to inform business decisions and enhance overall performance?
3. Takeaways for New Social Media Platforms:
   • What lessons can be drawn from the experiences of developing a social media platform in 2023?
   • What key principles should guide the development of new platforms to navigate the challenges effectively?

Developing a social media platform in 2023 is not just a technical endeavor; it's a strategic dance that requires a keen understanding of user expectations, data utilization, and the evolving landscape. This case study aims to explore these challenges, propose solutions, and provide valuable insights for both existing and future social media platforms.

🛠️ Data Operations and Management

This project deals with a large dataset, and to ensure effective data cleansing and operations, Python v3.12 is utilized for data management. Python's versatility and rich ecosystem of libraries make it an ideal choice for handling the complexities of social media data.

🐍 Python Requirements

Python Requirements (Side Heading)

Let's install all the prerequisite libraries for the operations from requirements.txt:

git init
git clone "repo"
pip install -r requirements.txt

requirements.txt

os
pandas
numpy
matplotlib

🚀 Post-Installation Operations

After all the libraries are installed in the respective virtual environment, data operations such as data cleaning, filling the data, etc., are performed. Check out the data folder for the data used in this project and the pandas folder to see how the data is handled.

📚 Resources & References

Resources: Online data available for the startup social media platform.

Case Study: Forage provides a comprehensive case study that gives a brief about the project. You can find the document here.

Visit their site: Social Buzz

👍 Solution and Key Takings from Social Buzz

🔍 First Key Insight: Analyzed their ALGORITHM analysis from big data

The primary focus is on enhancing user experience by providing users with content aligned with their preferences and desires, particularly the most viewed content across the platform. This dual strategy not only improves individual user experiences but also contributes to creating a shared digital space where personal choices and collective appeal intersect. For instance, if a user frequently watches technology-related content, the algorithm prioritizes and promotes more technology-related content, along with other popular content. This exemplifies a crucial aspect of how the algorithm operates in the digital space.

📉 Second Key Insight:

In dissecting the ebb and flow of user engagement, a distinctive pattern emerges. From April to July, we witnessed a robust surge, maintaining momentum through a stable July to October. However, a noteworthy shift occurred from October to January, revealing a gradual 15% decline. Delving deeper, the subsequent January to April interval witnessed a further 10% dip, culminating in an overall reduction of 25%.

This intriguing trend aligns with a plausible explanation: the holiday season effect. Users, potentially occupied with festivities, showed a natural dip in mobile usage and subsequent social media engagement. Understanding this nuanced rhythm unveils a strategic opportunity: crafting targeted campaigns and features to reignite engagement during post-holiday phases, ensuring a resilient bounce-back for sustained growth.

Check out the data folder for the data used here, and the pandas folder to see how the data is handled.

📊 Tableau for Visualization

Tableau is utilized for effective visualization of the data trends and patterns. The visualizations provide a comprehensive understanding of the insights derived from the social media platform data.