Student Social Media Addiction Dataset

# Load necessary library
library(tidyverse)

# Read the dataset
data <- read_csv("Students Social Media Addiction.csv")

Rows: 705 Columns: 13
── Column specification ────────────────────────────────────────────────────────────
Delimiter: ","
chr (6): Gender, Academic_Level, Country, Most_Used_Platform, Affects_Academic_P...
dbl (7): Student_ID, Age, Avg_Daily_Usage_Hours, Sleep_Hours_Per_Night, Mental_H...

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

Prepare the environment by loading necessary tools (tidyverse) and import a dataset about students’ social media addiction for subsequent analysis.

model <- lm(Addicted_Score ~ Sleep_Hours_Per_Night, data = data)
summary(model)

Call:
lm(formula = Addicted_Score ~ Sleep_Hours_Per_Night, data = data)

Residuals:
    Min      1Q  Median      3Q     Max 
-3.2184 -0.7570  0.0884  0.7347  2.4280 

Coefficients:
                      Estimate Std. Error t value Pr(>|t|)    
(Intercept)           13.83680    0.23820   58.09   <2e-16 ***
Sleep_Hours_Per_Night -1.07730    0.03422  -31.48   <2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 1.023 on 703 degrees of freedom
Multiple R-squared:  0.585, Adjusted R-squared:  0.5844 
F-statistic:   991 on 1 and 703 DF,  p-value: < 2.2e-16

Students’ nightly sleep and their social media addiction scores relationship.

# Load libraries
library(tidyverse)

# Read the data
data <- read.csv("Students Social Media Addiction.csv")

# Linear regression model
model_linear <- lm(Addicted_Score ~ Sleep_Hours_Per_Night, data = data)

# Summary of the model
summary(model_linear)

Call:
lm(formula = Addicted_Score ~ Sleep_Hours_Per_Night, data = data)

Residuals:
    Min      1Q  Median      3Q     Max 
-3.2184 -0.7570  0.0884  0.7347  2.4280 

Coefficients:
                      Estimate Std. Error t value Pr(>|t|)    
(Intercept)           13.83680    0.23820   58.09   <2e-16 ***
Sleep_Hours_Per_Night -1.07730    0.03422  -31.48   <2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 1.023 on 703 degrees of freedom
Multiple R-squared:  0.585, Adjusted R-squared:  0.5844 
F-statistic:   991 on 1 and 703 DF,  p-value: < 2.2e-16

library(tidyverse)

# Load your CSV file
data <- read.csv("Students Social Media Addiction.csv")

# Check structure
glimpse(data)

Rows: 705
Columns: 13
$ Student_ID                   <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14…
$ Age                          <int> 19, 22, 20, 18, 21, 19, 23, 20, 18, 21, 19, 2…
$ Gender                       <chr> "Female", "Male", "Female", "Male", "Male", "…
$ Academic_Level               <chr> "Undergraduate", "Graduate", "Undergraduate",…
$ Country                      <chr> "Bangladesh", "India", "USA", "UK", "Canada",…
$ Avg_Daily_Usage_Hours        <dbl> 5.2, 2.1, 6.0, 3.0, 4.5, 7.2, 1.5, 5.8, 4.0, …
$ Most_Used_Platform           <chr> "Instagram", "Twitter", "TikTok", "YouTube", …
$ Affects_Academic_Performance <chr> "Yes", "No", "Yes", "No", "Yes", "Yes", "No",…
$ Sleep_Hours_Per_Night        <dbl> 6.5, 7.5, 5.0, 7.0, 6.0, 4.5, 8.0, 6.0, 6.5, …
$ Mental_Health_Score          <int> 6, 8, 5, 7, 6, 4, 9, 6, 7, 7, 5, 6, 8, 5, 7, …
$ Relationship_Status          <chr> "In Relationship", "Single", "Complicated", "…
$ Conflicts_Over_Social_Media  <int> 3, 0, 4, 1, 2, 5, 0, 2, 1, 1, 3, 2, 1, 4, 2, …
$ Addicted_Score               <int> 8, 3, 9, 4, 7, 9, 2, 8, 5, 4, 7, 8, 4, 9, 5, …

# Convert outcome variable to binary (1 = Yes, 0 = No)
data$Academic_Binary <- ifelse(data$Affects_Academic_Performance == "Yes", 1, 0)

library(dplyr)
library(ggplot2)

line_data <- data %>%
  group_by(Avg_Daily_Usage_Hours) %>%
  summarise(mean_mental_health = mean(Mental_Health_Score, na.rm = TRUE))

ggplot(line_data, aes(x = Avg_Daily_Usage_Hours, y = mean_mental_health)) +
  geom_point(color = "black", size = 1.5) +
  geom_smooth(method = "lm", color = "blue") +
  labs(title = "Avg Social Media Usage vs Mental Health",
       x = "Average Daily Usage (hours)",
       y = "Average Mental Health Score") +
  theme_minimal()

`geom_smooth()` using formula = 'y ~ x'

To see whether there’s a pattern or trend between how much time students spend on social media and their mental health.

library(dplyr)
library(ggplot2)

line_data2 <- data %>%
  group_by(Sleep_Hours_Per_Night) %>%
  summarise(mean_addicted_score = mean(Addicted_Score, na.rm = TRUE))

ggplot(line_data2, aes(x = Sleep_Hours_Per_Night, y = mean_addicted_score)) +
  geom_point(color = "black") +
  geom_smooth(method = "lm", color = "red", se = TRUE) +
  labs(title = "Sleep Hours vs Addicted Score",
       x = "Sleep Hours Per Night",
       y = "Average Addicted Score") +
  theme_minimal()

`geom_smooth()` using formula = 'y ~ x'

The chart shows that the more one sleeps, the lower the degree of addiction to social media

ggplot(data, aes(x = as.factor(Addicted_Score), y = Sleep_Hours_Per_Night)) +
  geom_boxplot(fill = "lightblue") +
  labs(title = "Sleep Hours by Addiction Score",
       x = "Addicted Score",
       y = "Sleep Hours per Night")

The chart shows that the higher the addiction, the less sleep time

usage_summary <- data %>%
  group_by(Gender, Avg_Daily_Usage_Hours) %>%
  summarise(avg_mental_health = mean(Mental_Health_Score, na.rm = TRUE), .groups = 'drop')

ggplot(usage_summary, aes(x = Avg_Daily_Usage_Hours, y = avg_mental_health, color = Gender)) +
  geom_point(size = 1.4) +
  geom_smooth(method = "lm", se = TRUE, size = 1.2) +
  labs(
    title = "Mental Health Score vs Social Media Usage by Gender",
    x = "Average Daily Social Media Usage (hours)",
    y = "Average Mental Health Score"
  ) +
  theme_minimal()

`geom_smooth()` using formula = 'y ~ x'

The chart shows that the longer the usage time, the lower the mental health score (negative impact).