IP PROJECT REPORT

PROJECT TITLE: Social Media Algorithms Explained Using Python

BY: Pratishtha Dangi, Renn Binn & PGT

CLASS: 12-K

1. ACKNOWLEDGEMENT
We would like to express our heartfelt gratitude to our school and the CBSE board for
encouraging practical learning through innovative projects. This project, titled "Social
Media Algorithms Explained Using Python", provided us a unique opportunity to explore
real-world technology using classroom concepts. It helped us understand how
programming and data science apply to platforms we use daily.

We sincerely thank our teacher and project guide, who continuously motivated us,
clarified our doubts, and helped us stay on track during the project development. Their
constant support and insightful feedback were essential in shaping our understanding
and guiding us throughout the 30-day development period.

We are also grateful to our peers, friends, and online educational resources that aided
us in researching the topic, learning new libraries, and improving our code structure.
This project has been a truly enriching and collaborative experience, and we value the
exposure it gave us to real-life applications of Informatics Practices.

2. PROBLEM DEFINITION
Social media platforms like Instagram, YouTube, and Twitter display content to users
based on what is most likely to engage them. These decisions are made using algorithms
— sets of programmed rules that process data such as the number of likes, comments,
shares, and how users interact with a post. High-engagement posts are more likely to be
shown to more users.

For a school student, the logic behind these platforms often seems like a mystery. This
project aims to demystify that logic by creating a Python-based simulation that mimics
how posts are ranked based on engagement. It introduces students to the practical
usage of Python in the context of data handling, sorting, and visualization.
By using simplified datasets and Python libraries like Pandas and Matplotlib, we create
an environment that helps us analyze and visualize engagement trends. This hands-on
approach helps us better understand how platforms use engagement metrics to push or
suppress content — an important digital literacy skill in today’s age.

3. INTRODUCTION TO SOCIAL MEDIA ALGORITHMS

Social media algorithms are responsible for deciding what we see on our feeds. Whether
it’s a trending meme, a viral video, or an educational post — behind every piece of
content is a set of rules that determines its visibility. These algorithms vary from one
platform to another but often have one thing in common: they reward engagement.

Engagement is measured by how people interact with content — for example, by liking,
sharing, commenting, or watching. In our project, we simplify this idea by assuming that
each post has values for these metrics. We then calculate an overall engagement score
for each post and rank the posts based on that score.

Python, a beginner-friendly yet powerful programming language, provides excellent

tools for such simulations. We use Matplotlib to visualize our data and Pandas to store
and manipulate datasets efficiently. For instance, we can create bar graphs showing
which content types (News, Entertainment, Education) get the most engagement, or
line graphs that show how likes increase over time.

This project is a great example of how real-world technology meets education. It

introduces us to basic concepts of data analysis, ranking algorithms, and user behavior
simulation. While actual social media algorithms are much more complex and driven by
AI and machine learning, this project gives us a simplified but insightful perspective.

By working on this, we not only improved our coding skills but also learned to think
logically, solve problems creatively, and present data in meaningful ways. It truly
connects the world of academics with the digital world we live in.

4. OBJECTIVE
The primary objective of this project is to simulate a basic social media algorithm using
Python. This algorithm helps determine which posts should be shown first based on
engagement metrics. The project introduces students to basic concepts of data
collection, analysis, ranking, and visualization.

Specific objectives include:

- To structure a dataset containing post engagement metrics like likes, shares, and
comments.
- To compute engagement scores using Python and rank posts accordingly.
- To use visualization tools such as bar graphs and line charts for data interpretation.
- To relate programming concepts with real-world social media behavior.

By achieving these objectives, students will develop analytical thinking, logical

reasoning, and basic programming skills.

5. HARDWARE AND SOFTWARE SPECIFICATIONS

Hardware Requirements:
- A laptop or desktop computer
- Minimum 4 GB RAM
- Stable internet connection (for library access)

Software Requirements:
- Python 3.x
- Pandas Library
- Matplotlib Library
- Jupyter Notebook / Python IDE (e.g., VSCode or PyCharm)

6. LIMITATIONS
While the project achieves its core goals, it also has certain limitations:

- The dataset used is small and manually created, limiting scalability.

- Actual social media algorithms are powered by AI and machine learning, which are not
covered here.
- Factors like user watch-time, behavior prediction, network effects, and trending scores
are not implemented.
- The engagement calculation uses basic weights, whereas real algorithms adapt
dynamically.

Despite these limitations, the project is effective for an introductory understanding of

algorithmic ranking.

7. CONCLUSION
Through this project, we successfully simulated a simplified social media post-ranking
system using Python. It helped us understand how platforms decide what content is
promoted, using engagement data as a metric.
We practiced structuring datasets, writing logic to compute scores, and visualizing the
results in graph format. This has given us valuable insight into how programming is used
in the real world — not just for computation, but for decision-making and content
delivery.

The project helped reinforce key Informatics Practices concepts, and we look forward to
exploring more advanced topics like machine learning and big data in the future.

8. BIBLIOGRAPHY
- CBSE Informatics Practices Textbook
- https://pandas.pydata.org
- https://matplotlib.org
- https://python.org
- Educational blogs and tutorials on social media algorithms