Social Media Usage vs Sleep, Stress & Productivity

By shrijeetverma13 · April 30, 2026

This dataset explores the relationship between social media usage, sleep patterns, stress levels, and productivity among individuals. With the rapid…

The bar chart shows average productivity scores across social media platforms. Twitter is associated with the highest productivity score (51.51), while LinkedIn has the lowest average productivity score (49.58). The overall difference between the highest and lowest platforms is just 1.93 points, suggesting relatively similar productivity levels across platforms.

The analysis compared social media usage and productivity scores across age groups from 16 to 49. Two visualizations were generated: a grouped bar chart showing average social media hours and productivity scores side by side for each age group, and a scatter plot highlighting how each age group clusters based on these two metrics. These charts make it easy to visually identify which groups use social media the most and where productivity dips the lowest.

The analysis produced two interactive visualizations exploring how sleep hours vary across stress levels and which platforms are associated with the highest stress. A box plot shows the distribution of sleep hours for each stress level category, and a stacked bar chart breaks down the percentage of users at each stress level across different social media platforms.

The analysis shows that exercise levels have very little correlation with productivity scores or stress levels in this dataset. Two charts were generated showing productivity and stress distribution across exercise groups (Low, Moderate, High, and Very High), and the correlations are nearly zero — meaning exercise alone doesn't strongly predict either outcome here.

The analysis successfully identified and compared the behavioral profiles of the top 10% (1,100 users, productivity score ≥ 90.65) versus the bottom 10% (1,101 users, productivity score ≤ 10.72) of productivity scorers. Two visualizations were generated to illustrate the differences: a grouped bar chart comparing average behavioral metrics across both groups, and a stress level distribution chart showing how stress varies between the two groups.

The analysis reveals that daily screen time has virtually no overall correlation with productivity scores (r = -0.002), meaning screen time alone is not a meaningful predictor of productivity across the dataset. Three visualizations were generated to explore this relationship in depth across different user segments.

The IQR outlier detection analysis was completed for productivity score, sleep hours, and social media hours. The results show that no outliers were detected in any of the three columns using the standard 1.5x IQR rule. Box plots were generated showing the distributions of all three columns, and a comparison chart was also produced. Since no productivity score outliers were identified, there are no extreme-value users to compare against normal users for sleep or social media patterns.

The analysis produced two visualizations comparing behavioral metrics across stress levels. The grouped bar chart shows average values for social media hours, sleep hours, exercise minutes, and productivity score broken down by Low, Medium, and High stress categories. A second chart displays the percentage difference between High and Low stress groups for each metric, with red bars indicating metrics that are lower in high-stress individuals and green bars showing metrics that increase with stress.

The Pearson correlation analysis has been completed for all 6 numeric variables, with two visualizations produced: a full correlation heatmap and a bar chart showing each variable's relationship with productivity score. The heatmap uses a red-blue color scale where deep blue indicates strong positive correlations and deep red indicates strong negative correlations. The bar chart ranks all variables by their correlation strength with productivity score, making it easy to see which factors help or hurt productivity.

The analysis ranked all 5 platforms (Instagram, Twitter, LinkedIn, Snapchat, YouTube) across four health and productivity dimensions. Instagram emerged as the most balanced and healthy platform with the lowest composite rank score of 9, followed by Twitter (11), LinkedIn (12), and Snapchat and YouTube tied at 13. A radar/spider chart and ranked table were generated to visualize these comparisons across all four dimensions simultaneously.