Scribd
Upload
2 views3 pages

Project Proposal

The project proposal by Matan Yakir aims to investigate how social media usage affects emotional well-being and to develop a predictive model based on this relationship. Utilizing a dataset from Kaggle that includes user demographics, social media activity, and emotional states, the project will involve data preprocessing, exploratory analysis, correlation analysis, predictive modeling, and feature importance analysis. The goal is to provide insights that could help individuals use social media in healthier ways.

Uploaded by

aharonirk
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
2 views3 pages

Project Proposal

The project proposal by Matan Yakir aims to investigate how social media usage affects emotional well-being and to develop a predictive model based on this relationship. Utilizing a dataset from Kaggle that includes user demographics, social media activity, and emotional states, the project will involve data preprocessing, exploratory analysis, correlation analysis, predictive modeling, and feature importance analysis. The goal is to provide insights that could help individuals use social media in healthier ways.

Uploaded by

aharonirk
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

Project Proposal

Introduction to Data Science


Matan Yakir

Research Question

How does the way people use social media (like time spent, number
of posts, and likes received) affect their emotional well-being? Can
we build a model to predict how someone feels emotionally based
on their social media activity?

Why this topic?


I don’t use social media myself, but I know it’s a big part of people’s
lives today. I want to understand how social media habits influence
emotions. This knowledge could help people use these platforms in
healthier ways.

Dataset

Source: Kaggle – Social Media Usage and Emotional Well-Being


Dataset

What’s in the dataset?


The dataset has information about users and their social media
habits. It includes:

 Age and Gender: Details about the user.

 Social media activity: Time spent, number of posts, likes


and comments received, and messages sent.

 Emotional state: A label that shows how the user feels (e.g.,
Happy, Sad, or Neutral).

Why is it relevant?
This dataset is perfect for my question because it has both social
media activity and emotional states. It gives me enough data to
explore how they’re connected.
Methods

1. Data Preprocessing:

o Handle missing values and outliers.

o Encode categorical variables (e.g., Gender, Platform,


Emotional_state) using appropriate techniques.

o Normalize numerical features for uniformity.

2. Exploratory Data Analysis (EDA):

o Visualize distributions of individual features.

o Analyze relationships between social media usage


metrics and emotional states using box plots, violin
plots, and heatmaps.

o Identify trends and patterns that warrant further


investigation.

3. Correlation Analysis:

o Compute correlation coefficients between numerical


features.

o Assess statistical significance to determine meaningful


relationships.

4. Predictive Modeling:

o Split the data into training and testing sets.

o Implement classification algorithms (e.g., Random


Forest, Support Vector Machine) to predict emotional
states based on usage patterns.

o Evaluate model performance using metrics such as


accuracy, precision, recall, and F1-score.

o Perform cross-validation to ensure model robustness.

5. Feature Importance Analysis:

o Determine which social media usage metrics most


significantly influence emotional state predictions.

o Interpret these findings to provide actionable insights.

You might also like