Smartphone Usage And Addiction Analysis

By shrijeetverma13 · March 14, 2026

Data source:

The bar chart displays the proportion of users classified as addicted at each stress level. The visualization breaks down addiction rates as percentages, making it easy to compare how stress levels relate to addiction classification across the user base.

The bar chart and data table show how much weekend screen time exceeds daily screen time, broken down by addiction level. The visualization clearly compares the average excess hours for each addiction level group, making it easy to spot which groups spend significantly more time on screens during weekends versus regular days.

A bar chart and data table have been generated showing smartphone addiction rates broken down by age group (18-20, 21-23, 24-26, 27-29, 30-32, and 33-35). The visualization uses a red color scale to highlight which groups have the highest addiction rates, making it easy to spot the most affected demographics at a glance.

The grouped bar chart and data tables show how daily screen time, gaming, and social media hours compare across Female, Male, and Other gender groups. The differences between genders are remarkably small across all three metrics.

A data table has been generated showing the average number of notifications per day for each addiction level (None, Mild, Moderate, Severe). The table breaks down how daily notification counts relate to increasing addiction levels, helping identify where the biggest jump — the tipping point — occurs between consecutive levels.

The age-gender combination with the highest percentage of addicted users is Age 24, Other gender, with 80.99% addiction rate — that's 98 out of 121 users in this group classified as addicted. A bar chart showing the Top 15 Age-Gender Combinations by % Addicted Users has been generated, along with supporting data tables for further exploration.

Users who report a negative academic/work impact (Yes) average 7.49 hours of daily screen time, 2.01 hours of gaming, and 3.28 hours of social media usage. This group includes 3,747 users. A grouped bar chart and comparison tables were generated to visualize these metrics across both impact groups.

Gaming hours and social media hours do not meaningfully influence each other — they appear to be completely independent behaviors. The correlation coefficient is essentially zero (-0.0009), meaning users who game more do not consistently spend less or more time on social media.

The analysis produced a box plot comparing app opens per day across four addiction level categories: None, Mild, Moderate, and Severe. The visualization clearly shows how daily app usage patterns differ between these groups.

Among the 2,474 users who sleep fewer than 6 hours per night, 1,701 of them — or 68.8% — are classified as addicted (addicted label=1). This is a notably high proportion, suggesting a strong link between insufficient sleep and addiction classification.

The analysis produced two visualizations showing how addiction levels are distributed across the dataset. A pie chart displays the overall share of each addiction level category, and a grouped bar chart breaks down those categories by gender, letting you compare how different genders are represented at each addiction level.

Among the 1,845 users who game more than 3 hours, the average sleep is 6.76 hours. Stress levels are fairly evenly spread but lean slightly toward High (632 users), followed by Low (621) and Medium (592). For academic or work impact, a slight majority — 932 users — report that gaming does impact their academics or work, compared to 913 who say it does not. A bar chart showing the stress level distribution has been generated for easy comparison.

The bar chart shows how addiction rates vary across four quartiles of daily screen time usage, from the lowest (Q1) to the highest (Q4) screen time groups. The visualization uses a red color scale to highlight differences in addiction rates across these groups, making it easy to spot which screen time ranges are associated with higher addiction levels.

The analysis shows virtually no relationship between gaming/social media hours and work/study hours. The scatter plot and bar chart both confirm this finding visually.

Gaming hours are remarkably similar between the two age groups. Users aged 18-24 average 2.04 hours of gaming per day, while users aged 25-35 average 2.00 hours — a difference of just 0.04 hours. Two visualizations were generated: an overlapping histogram showing the distribution of gaming hours for both groups, and a box plot comparing the spread and median values side by side.

The analysis identified 457 users who exhibit compulsive checking behavior — they open apps frequently (≥140 times/day) but spend relatively little time in them (≤5.2 hours/day). A scatter plot highlights these users in red against the normal population in blue, and a detailed table ranks the top compulsive checkers by their opens-per-hour ratio.

For addicted users, there is virtually no linear relationship between daily screen time and sleep hours. The Pearson correlation of 0.0004 is essentially zero, meaning screen time does not predict how much sleep addicted users get. A scatter plot with a trend line has been generated to visualize this finding.