Social Media Insights: Exploring User Behavior and Trends
2023-11-05
The scatter plot shows the relationship between the number of followers and the number of posts for Instagram users with more than 1000 followers. The blue points represent users with more than 1000 followers, and the red points represent users with more than 100 posts but fewer than 1000 followers.
plot(data[data$`How many followers do you have on Instagram?` > 1000, ]$`How many followers do you have on Instagram?`, data[data$`How many followers do you have on Instagram?` > 1000, ]$`How many posts do you have on Instagram?`, col = "blue", xlab = "Number of followers", ylab = "Number of posts")
points(data[data$`How many followers do you have on Instagram?` <= 1000 & data$`How many posts do you have on Instagram?` > 100, ]$`How many followers do you have on Instagram?`, data[data$`How many followers do you have on Instagram?` <= 1000 & data$`How many posts do you have on Instagram?` > 100, ]$`How many posts do you have on Instagram?`, col = "red")
legend("topright", legend = c("More than 1000 followers", "More than 100 posts"), col = c("blue", "red"), pch = 1)
.
require(ggplot2)## Loading required package: ggplot2# Create a pie chart for gender distribution
ggplot(data, aes(x = "", fill = Gender)) +
geom_bar(width = 1) +
coord_polar(theta = "y") +
labs(title = "Gender Distribution", fill = "Gender")
## The pie chart shows the gender distribution of a user. The pie is
divided into three slices, representing females, males, and non-binary
individuals. The slices are colored green, blue, and light red color
# Create a histogram for age distribution
ggplot(data, aes(x = Age, fill = factor(Age))) +
geom_histogram(binwidth = 5, color = "black") +
scale_fill_viridis_d() +
labs(title = "Age Distribution", x = "Age", y = "Count") +
theme_minimal()
The age distribution chart shows the number of people in each age group for a given population. The x-axis shows the age group, and the y-axis shows the number of people in that age group. The bars in the chart are colored according to the age group
# Create a bar chart with education level
ggplot(data, aes(x = `Highest Education`, fill = Gender)) +
geom_bar(color = "black", size = 0.5, width = 0.7, position = position_dodge()) +
labs(title = "Education Level Distribution", x = "Education Level", y = "Count") +
theme_minimal() +
theme(legend.position = "top", legend.title = element_blank()) +
scale_fill_manual(values = c("#FFC0CB", "#ADD8E6", "#90EE90")) +
guides(fill = guide_legend(reverse = TRUE)) +
geom_text(aes(label=after_stat(count)), stat='count', position=position_dodge(width=0.7), vjust=-0.5, size=3)## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
## The bar chart shows the distribution of education levels for males,
females, and non-binary people in the data. The x-axis shows the
education level, and the y-axis shows the count of people. The bars are
grouped by gender, and the colors of the bars represent the gender (pink
for females, blue for males, and green for non-binary people).
# Create a bar chart with phone operating system
ggplot(data, aes(x = `Phone OS`, fill = Gender)) +
geom_bar() +
labs(title = "Phone Operating System Distribution", x = "Phone Operating System", y = "Count")
## The bar chart shows the distribution of phone operating systems by
gender. The y-axis shows the count of people using each operating
system, and the x-axis shows the operating system. The bars are colored
by gender. The chart shows that Android is the most popular operating
system for all gender
library(ggplot2)
# Create a ggplot bar chart for Gender by Zone/Area with Total Social Media Usage
ggplot(data, aes(x = `Zone`, y = `Total Social Media Usage`, fill = Gender)) +
geom_bar(stat = "identity", position = "dodge") +
labs(x = "Zone/Area", y = "Total Social Media Usage", title = "Gender by Zone/Area with Total Social Media Usage") +
scale_fill_brewer(palette = "Set3") + # Choose a colorful palette
theme_minimal()
## The bar graph shows the total social media usage by gender, by
zone/area. The zones/areas are Central, Eastern, North-Eastern,
Northern, Southern, and Western. the genders are Female, Male, and
Non-Binary. The total social media usage is highest in the Western zone,
The total social media usage is lowest in the central zone .
# Create a pie chart for phone operating system distribution
ggplot(data, aes(x = "", fill = `Phone OS`)) +
geom_bar(width = 1) +
coord_polar(theta = "y") +
labs(title = "Phone Operating System Distribution", fill = "Phone Operating System")
## The pie chart shows the distribution of phones by operating system.
The largest slice is for Android and lowest slice in others phone
operating system
# Create a scatter plot for time spent on Facebook and Instagram
ggplot(data, aes(x = `Time Spent on Facebook in last week (in minutes)`, y = `Time Spent on Instagram in last week (in minutes)`)) +
geom_point(color = "#FFC0CB") +
labs(title = "Time Spent on Facebook vs. Time Spent on Instagram", x = "Time Spent on Facebook (in minutes)", y = "Time Spent on Instagram (in minutes)") 
## the scatter plot shows a positive correlation between time spent on
Facebook and time spent on Instagram. This means that people who spend
more time on Facebook also spend more time on Instagram. The scatter
plot also shows that there are more people who spend more time on
Facebook than on Instagram.
# Create a histogram for social media usage distribution
ggplot(data, aes(x = `Total Social Media Usage`)) +
geom_histogram(binwidth = 500, fill = "#FFC0CB", color = "black") +
labs(title = "Social Media Usage Distribution", x = "Total Social Media Usage (in minutes)", y = "Count") +
theme_minimal() +
theme(plot.background = element_rect(fill = "#ADD8E6"),
axis.text = element_text(size = 12, color = "black"),
axis.title = element_text(size = 14, color = "black"),
plot.title = element_text(size = 16, color = "black"))
This is histogram of social media usage distribution. It shows the number of people who use social media for a certain amount of time each day. The x-axis of the chart shows the total social media usage in minutes, and the y-axis shows the number of people who use social media for that amount of time.
library(ggplot2)
# Create a ggplot bar chart
ggplot(data, aes(x=`Profession/Activity`, y=`Total Social Media Usage`, fill=`Profession/Activity`)) +
geom_bar(stat="identity") +
labs(x="Profession/Activity", y="Total Social Media Usage", title="Total Social Media Usage by Profession/Activity") +
theme_minimal() +
scale_fill_brewer(palette="Set3") # Choose a colorful palette
## The chart shows the total social media usage by profession/activity.
The x-axis shows the different professions/activities, and the y-axis
shows the total social media usage in hours per week. The bars are
colored by profession/activity.
# Create a histogram for time spent on WhatsApp distribution
ggplot(data, aes(x = `Time Spent on WhatsApp in last week (in minutes)`, fill = Gender)) +
geom_histogram(binwidth = 100) +
labs(title = "Time Spent on WhatsApp Distribution", x = "Time Spent on WhatsApp (in minutes)", y = "Count")
the graph shows that WhatsApp is a popular communication platform for people of all genders, with females spending slightly more time on it than males.
# Create a bar chart for education level and social media usage
ggplot(data, aes(x = `Highest Education`, y = `Total Social Media Usage`, fill = `Highest Education`)) +
geom_bar(stat = "summary", fun = "mean") +
labs(title = "Education Level vs. Social Media Usage", x = "Education Level", y = "Total Social Media Usage (in minutes)") +
scale_fill_manual(values = c("#FFC0CB", "#ADD8E6", "#90EE90", "#FFD700")) +
theme_minimal() 
## The chart shows the total social media usage (in minutes) of people
with different levels of education. The bar graph shows that people with
higher education levels use social media more than those with other
education levels.
# Distribution of the number of posts on Instagram
ggplot(data, aes(x = `How many posts do you have on Instagram?`)) +
geom_histogram(binwidth = 50, fill = "#ADD8E6") +
labs(title = "Number of Posts on Instagram Distribution", x = "Number of Posts on Instagram", y = "Count") +
theme_minimal()
## The shows the distribution of Instagram posts by country. The x-axis
shows the number of posts on Instagram , and the y-axis shows the
count.
# Relationship between age and the number of posts on Instagram
ggplot(data, aes(x = Age, y = `How many posts do you have on Instagram?`, color = Age)) +
geom_point() +
labs(title = "Age vs Number of Posts on Instagram", x = "Age", y = "Number of Posts on Instagram")
## This chart shows the relationship between age and the number of posts
on Instagram. The x-axis represents the age of the user, and the y-axis
represents the number of posts that the user has made on Instagram. The
chart shows that, younger users post more on Instagram than older users.
There are a few possible explanations for this trend. First, younger
users may simply have more time to spend on social media. Second,
younger users may be more likely to use social media to connect with
their friends and family. Third, younger users may be more likely to use
social media to express themselves and share their creativity.
# Relationship between age and the time spent on Facebook
ggplot(data, aes(x = Age, y = `Time Spent on Facebook in last week (in minutes)`, color = Age)) +
geom_point() +
labs(title = "Age vs Time Spent on Facebook", x = "Age", y = "Time Spent on Facebook (in minutes)")
## the bar chart shows the distribution of time spent on Facebook in the
last week, measured in minutes. and the height of each bar represents
the number of people who spent that amount of time on Facebook. with a
majority of users spending a relatively small amount of time on Facebook
each week and a smaller group of users spending a significant amount of
time on Facebook each week.
# Relationship between age and the time spent on Instagram
ggplot(data, aes(x = Age, y = `Time Spent on Instagram in last week (in minutes)`, color = Age)) +
geom_point() +
labs(title = "Age vs Time Spent on Instagram", x = "Age", y = "Time Spent on Instagram (in minutes)")
## The chart shows a positive correlation between age and time spent on
Instagram, meaning that younger users spend more time on the platform
than older age users. One possibility is that younger users have more
time to spend on social media in general.
# Distribution of the total social media usage
ggplot(data, aes(x = `Total Social Media Usage`, fill = Gender)) +
geom_histogram(binwidth = 500) +
labs(title = "Total Social Media Usage Distribution", x = "Total Social Media Usage", y = "Count") +
scale_fill_manual(values = c("#ADD8E6", "#FFC0CB", "#FF0000")) + # Add a third color value
theme_minimal() +
theme(legend.position = "bottom")
The chart shows the distribution of total social media usage by gender. It is a histogram, with the x-axis showing total social media usage and the y-axis showing the number of people. The bars are color-coded by gender, with blue representing females, pink representing males, and red representing non-binary individuals.
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.3 ✔ stringr 1.5.0
## ✔ forcats 1.0.0 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.0
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(ggplot2)
library(maps)## Warning: package 'maps' was built under R version 4.3.2##
## Attaching package: 'maps'
##
## The following object is masked from 'package:purrr':
##
## mapdata <- read_csv("C:/Users/bhaga/OneDrive/Desktop/new dataset/social media_new.csv")## Rows: 1628 Columns: 40
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (15): City, Current Status, Do you own multiple profiles on Instagram?, ...
## dbl (11): Age, Latitude, Longitude, How many subscriber do you have on youtu...
## num (14): How many followers do you have on Instagram?, How many posts do yo...
##
## 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.# Create a ggplot object with your dataset
p <- ggplot(data, aes(x = Longitude, y = Latitude, color = State, fill = State)) +
geom_point(size = 3) + # Add points to represent data with size
coord_fixed(ratio = 1) + # Aspect ratio
theme_minimal() # Plain background theme
# Add India map outline
india_map <- map_data("world", region = "India")
p <- p + geom_polygon(data = india_map, aes(x = long, y = lat, group = group), fill = NA, color = "black")
print(p)
## The chart shows the social media users in India, by state. the color
of the point represents the state.The states with the most social media
users are Uttar Pradesh, Maharashtra, and West Bengal. The states with
the fewest social media users are Jammu and Kashmir, Uttarakhand, and
Himachal Pradesh.
# Relationship between age and the total social media usage
library(ggplot2)
# Create a scatter plot with color and a specific theme
ggplot(data, aes(x = Age, y = `Total Social Media Usage`, color = Age)) +
geom_point() +
labs(title = "Age vs Total Social Media Usage", x = "Age", y = "Total Social Media Usage") 
## The chart shows a scatter plot of age vs total social media usage.
The data points are colored by age, with younger people represented by
darker colors and older people represented by lighter colors.The overall
shows that younger people use social media more than older people. where
the x-axis (age) and the y-axis (total social media usage). One
possibility is that younger people are more likely with social media and
more comfortable using it.
# Relationship between the number of followers on Instagram and the number of posts on Instagram
ggplot(data, aes(x = `How many followers do you have on Instagram?`, y = `How many posts do you have on Instagram?`)) +
geom_point() +
labs(title = "Number of Followers vs Number of Posts on Instagram", x = "Number of Followers on Instagram", y = "Number of Posts on Instagram")
## The chart shows a positive correlation between the number of
followers on Instagram and the number of posts on Instagram, Instagram
users with more followers have more posts. with some users with a high
number of followers having a low number of posts.
# Pie chart for current status distribution
ggplot(data, aes(x = "", fill = `Current Status`)) +
geom_bar(width = 1) +
coord_polar(theta = "y") +
labs(title = "Current Status Distribution", fill = "Current Status")
## The pie chart shows the distribution of people in different current
status, such as Sabbatical, Self Employed, Student, and Working
professional. The chart is labeled “Current Status Distribution” and the
legend shows the colors used to represent each status.
#.******************************************************************************************************************************************
# Read the CSV file
data <- read_csv("C:/Users/bhaga/OneDrive/Desktop/new dataset/social media_new.csv")## Rows: 1628 Columns: 40
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (15): City, Current Status, Do you own multiple profiles on Instagram?, ...
## dbl (11): Age, Latitude, Longitude, How many subscriber do you have on youtu...
## num (14): How many followers do you have on Instagram?, How many posts do yo...
##
## 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.# Load the ggplot2 package
library(ggplot2)
library(tidyverse)
# Sample data
data <- data <- data %>% select(Age,Gender,`Total WhatsApp Usage`,`Total Social Media Usage`,`Total Facebook Usage`,`Total Instagram Usage`,`Total YouTube Usage (minutes)`)
# Create a barplot for Age vs. Total Facebook Usage with Gender as a legend
ggplot(data, aes(x = Age, y = `Total Facebook Usage`, fill = Gender)) +
geom_bar(stat = "identity") +
labs(title = "Total Facebook Usage by Age and Gender", x = "Age Group", y = "Total Usage (minutes)") +
scale_fill_manual(values = c("Male" = "blue", "Female" = "pink")) +
theme_minimal()
The bar chart shows the total Facebook usage by age and gender. The x-axis shows the age group, and the y-axis shows the total Facebook usage in minutes. The bars are colored blue for males and pink for females. the chart shows that younger user are use more The highest total usage is in the 20-29 age group
# Create a barplot for Age vs. Total Instagram Usage with Gender as a legend
ggplot(data, aes(x = Age, y = `Total Instagram Usage`, fill = Gender)) +
geom_bar(stat = "identity") +
labs(title = "Total Instagram Usage by Age and Gender", x = "Age Group", y = "Total Usage (minutes)") +
scale_fill_manual(values = c("Male" = "blue", "Female" = "red")) +
theme_minimal()
## The bar chart shows the total Instagram usage by age and gender. The
chart is labeled “Total Instagram Usage by Age and Gender” and the
x-axis shows the age group, while the y-axis shows the total instagram
usage in minutes. The chart is color-coded by gender, with male users in
blue and female users in red.
# Create a barplot for Age vs. Total WhatsApp Usage with Gender as a legend
ggplot(data, aes(x = Age, y = `Total WhatsApp Usage`, fill = Gender)) +
geom_bar(stat = "identity") +
labs(title = "Total WhatsApp Usage by Age and Gender", x = "Age Group", y = "Total Usage (minutes)") +
scale_fill_manual(values = c("Male" = "maroon", "Female" = "pink")) +
theme_minimal()
## The bar chart shows the total WhatsApp usage by age and gender. The
x-axis shows the age group, and the y-axis shows the total usage in
minutes. The bars are colored with gender, maroon for males and pink for
females. The chart shows that overall, female use WhatsApp more than
male
# Create a barplot for Age vs. Total YouTube Usage with Gender as a legend
ggplot(data, aes(x = Age, y = `Total YouTube Usage (minutes)`, fill = Gender)) +
geom_bar(stat = "identity") +
labs(title = "Total YouTube Usage by Age and Gender", x = "Age Group", y = "Total Usage (minutes)") +
scale_fill_manual(values = c("Male" = "maroon", "Female" = "skyblue")) +
theme_minimal()
## The bar chart you have sent shows the total YouTube usage by age and
gender. The chart is labeled “Total YouTube Usage by Age and Gender” and
the x-axis shows the age group, while the y-axis shows the total usage
in minutes. The chart is colored by gender, with male users in maroon
and female users in sky-blue. the chart shows that Female users use
YouTube more than male users in all age groups
# Combine all the data into a long format
data_long <- data %>%
pivot_longer(cols = c(`Total Facebook Usage`, `Total Instagram Usage`, `Total WhatsApp Usage`, `Total YouTube Usage (minutes)`),
names_to = "Platform", values_to = "Total Usage")
# Create a single plot with facets
ggplot(data_long, aes(x = Age, y = `Total Usage`, fill = Gender)) +
geom_bar(stat = "identity") +
labs(title = "Social Media Usage by Age and Gender", x = "Age Group", y = "Total Usage (minutes)") +
scale_fill_manual(values = c("Male" = "blue", "Female" = "red")) +
theme_minimal() +
facet_wrap(~ Platform, scales = "free_y")
Here all combined bar chart shows the total usage of four social media platforms (Facebook, Instagram, WhatsApp, and YouTube) by age and gender in minutes.
library(readr)
data <- read_csv("C:/Users/bhaga/OneDrive/Desktop/new dataset/social media_new.csv")## Rows: 1628 Columns: 40
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (15): City, Current Status, Do you own multiple profiles on Instagram?, ...
## dbl (11): Age, Latitude, Longitude, How many subscriber do you have on youtu...
## num (14): How many followers do you have on Instagram?, How many posts do yo...
##
## 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.# Load required library
library(ggplot2)
library(factoextra)## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBa# Create a data frame with the given data
data <- data[, c("Age", "Income from YouTube (rs,month)")]
# Perform k-means clustering with 2 clusters
set.seed(123) # For reproducibility
k <- 2
kmeans_result <- kmeans(data, centers = k)
# Add the cluster assignments to the original data
data$Cluster <- as.factor(kmeans_result$cluster)
# Print the cluster assignments
print(data)## # A tibble: 1,628 × 3
## Age `Income from YouTube (rs,month)` Cluster
## <dbl> <dbl> <fct>
## 1 24 88447 2
## 2 39 64764 2
## 3 22 4387 1
## 4 26 99695 2
## 5 50 81297 2
## 6 25 51770 2
## 7 52 38003 1
## 8 45 54216 2
## 9 25 48149 1
## 10 27 12657 1
## # ℹ 1,618 more rows# Elbow Method to determine the optimal number of clusters
wcss <- vector("numeric", length = 10) # Initialize a vector to store Within-Cluster Sum of Squares (WCSS)
# Calculate WCSS for different numbers of clusters (k)
for (i in 1:10) {
kmeans_temp <- kmeans(data[, c("Age", "Income from YouTube (rs,month)")], centers = i)
wcss[i] <- kmeans_temp$tot.withinss # Store the WCSS for the current k
}
# Plot the Elbow Method graph
plot(1:10, wcss, type = "b", xlab = "K (Number of Clusters)", ylab = "WCSS (Within-Cluster Sum of Squares)") # Set x and y axis labels
abline(v = k, col = "red", lty = 2) # Highlight the chosen k
# Visualization of the clustering with centroids
ggplot(data, aes(x = Age, y = `Income from YouTube (rs,month)`, color = Cluster)) +
geom_point() +
geom_point(data = as.data.frame(kmeans_result$centers), aes(x = Age, y = `Income from YouTube (rs,month)`), color = "darkred", size = 3, shape = 4) +
labs(title = "K-Means Clustering (k = 2) with Centroids", x = "Age", y = "Income from YouTube") +
scale_color_manual(values = c("blue", "green"))
## The chart shows the results of the Elbow Method for determining the
optimal number of clusters for k-means clustering. The Elbow Method
plots the Within-Cluster Sum of Squares (WCSS) for different numbers of
clusters (k). The WCSS is a measure of how well the data points fit into
their assigned clusters. A lower WCSS indicates that the data points are
more tightly clustered around their centroids.
The chart is a k-means clustering of data points based on their age and income from YouTube. K-means clustering is an unsupervised learning algorithm. The chart shows that the data points are clustered into two groups, with the blue cluster representing lower incomes and the green cluster representing higher incomes. The centroids of the two clusters are marked by the dark red X points.
library(readr)
library(dplyr)
library(ggplot2)
# Read the CSV file
data <- read_csv("C:/Users/bhaga/OneDrive/Desktop/new dataset/social media_new.csv")## Rows: 1628 Columns: 40
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (15): City, Current Status, Do you own multiple profiles on Instagram?, ...
## dbl (11): Age, Latitude, Longitude, How many subscriber do you have on youtu...
## num (14): How many followers do you have on Instagram?, How many posts do yo...
##
## 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.# Select the 'Age' and 'Total Social Facebook Usage' variables
data <- data %>% select(Age, `Total Facebook Usage`)
# Remove any rows with missing values
data <- na.omit(data)
# Convert the 'Age' variable to numeric
data$Age <- as.numeric(data$Age)
# Create a linear regression model
model <- lm(`Total Facebook Usage` ~ Age, data = data)
# Predict the next 5-year value
new_data <- data.frame(Age = c(31, 32, 33, 34, 35))
prediction <- predict(model, newdata = new_data)
# Add a 'Group' column to distinguish older and younger based on age threshold
data <- data %>%
mutate(Group = ifelse(Age > 35, "Older", "Younger"))
# Create a scatter plot with a smoothing line, colored by 'Group'
ggplot(data, aes(x = Age, y = `Total Facebook Usage`, color = Group)) +
geom_point() +
geom_smooth(method = "lm", se = FALSE, color = "blue") +
geom_point(data = new_data, aes(x = Age, y = prediction), color = "red", size = 3) + # Add points for predicted ages
labs(title = "Age vs. Total Facebook Usage", x = "Age", y = "Total Facebook Usage") +
scale_color_manual(values = c("Younger" = "green", "Older" = "purple")) +
geom_vline(xintercept = 35, linetype = "dashed") # Add a vertical dashed line at age 35## `geom_smooth()` using formula = 'y ~ x'
## Here I use linear regression shows the relationship between age and
total Facebook usage. The data is divided into two groups: younger users
(age 35 or below) and older users (age 36 or above). The vertical dashed
line at age 35 separates the two groups. Younger and older age groups ,
younger with green color and older with purple color . The blue line
represents the linear regression model that model is predict total
Facebook usage based on age. The chart shows that there is a positive
correlation between age and total Facebook usage. This means that as
people get older use Facebook more. This is likely because older people
have more time to spend on social media and are more likely to have
friends and family members who use Facebook. red data points are used to
predict the values for ages 31, 32, 33, 34, and 35 based on the linear
regression model.
library(readr)
library(dplyr)
library(ggplot2)
# Read the CSV file
data <- read_csv("C:/Users/bhaga/OneDrive/Desktop/new dataset/social media_new.csv")## Rows: 1628 Columns: 40
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (15): City, Current Status, Do you own multiple profiles on Instagram?, ...
## dbl (11): Age, Latitude, Longitude, How many subscriber do you have on youtu...
## num (14): How many followers do you have on Instagram?, How many posts do yo...
##
## 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.# Select the 'Age' and 'Total Instagram Usage' variables
data <- data %>% select(Age, `Total Instagram Usage`)
# Remove any rows with missing values
data <- na.omit(data)
# Convert the 'Age' variable to numeric
data$Age <- as.numeric(data$Age)
# Create a linear regression model
model <- lm(`Total Instagram Usage` ~ Age, data = data)
# Predict the next 5-year value
new_data <- data.frame(Age = c(31, 32, 33, 34, 35))
prediction <- predict(model, newdata = new_data)
# Add a 'Group' column to distinguish older and younger based on age threshold
data <- data %>%
mutate(Group = ifelse(Age > 35, "Older", "Younger"))
# Create a scatter plot with a smoothing line, colored by 'Group'
ggplot(data, aes(x = Age, y = `Total Instagram Usage`, color = Group)) +
geom_point() +
geom_smooth(method = "lm", se = FALSE,color = "blue") +
geom_point(data = new_data, aes(x = Age, y = prediction), color = "red", size = 3) +
labs(title = "Age vs. Total Instagram Usage", x = "Age", y = "Total Instagram Usage") +
scale_color_manual(values = c("Younger" = "maroon", "Older" = "blue")) +
geom_vline(xintercept = 35, linetype = "dashed") # Add a vertical dashed line at age 35## `geom_smooth()` using formula = 'y ~ x'
## Here I use linear regression shows the relationship between age and
total Instagram usage. The dataset is segmented into two distinct
groups: younger users (aged 35 or below) represented in purple, and
older users (aged 36 or above) shown in blue. A vertical dashed line at
age 35 separates these two groups. The blue line in the chart represents
the linear regression model, which predicts total Instagram usage based
on age, they younger use Instagram more frequently. red data points are
used to predict the values for ages 31, 32, 33, 34, and 35 based on the
linear regression model.
library(readr)
library(dplyr)
library(ggplot2)
# Read the CSV file
data <- read_csv("C:/Users/bhaga/OneDrive/Desktop/new dataset/social media_new.csv")## Rows: 1628 Columns: 40
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (15): City, Current Status, Do you own multiple profiles on Instagram?, ...
## dbl (11): Age, Latitude, Longitude, How many subscriber do you have on youtu...
## num (14): How many followers do you have on Instagram?, How many posts do yo...
##
## 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.# Select the 'Age' and 'Total WhatsApp Usage' variables
data <- data %>% select(Age, `Total WhatsApp Usage`)
# Remove any rows with missing values
data <- na.omit(data)
# Convert the 'Age' variable to numeric
data$Age <- as.numeric(data$Age)
# Create a linear regression model
model <- lm(`Total WhatsApp Usage` ~ Age, data = data)
# Predict the next 5-year value
new_data <- data.frame(Age = c(31, 32, 33, 34, 35))
prediction <- predict(model, newdata = new_data)
# Add a 'Group' column to distinguish older and younger based on age threshold
data <- data %>%
mutate(Group = ifelse(Age > 35, "Older", "Younger"))
# Create a scatter plot with a smoothing line, colored by 'Group'
ggplot(data, aes(x = Age, y = `Total WhatsApp Usage`, color = Group)) +
geom_point() +
geom_smooth(method = "lm", se = FALSE,color="blue") +
geom_point(data = new_data, aes(x = Age, y = prediction), color = "green", size = 3) +
labs(title = "Age vs. Total WhatsApp Usage", x = "Age", y = "Total WhatsApp Usage") +
scale_color_manual(values = c("Younger" = "red", "Older" = "blue")) +
geom_vline(xintercept = 35, linetype = "dashed") # Add a vertical dashed line at age 35## `geom_smooth()` using formula = 'y ~ x'
a linear regression model to explore the relationship between age and total WhatsApp usage. The dataset is focus on two key variables: ‘Age’ and ‘Total WhatsApp Usage.’ Rows with A linear regression model is then created, which predict ‘Total WhatsApp Usage’ based on an individual’s age. To gain expected usage in the coming five years and. A vertical dashed line is introduced at the age of 35. Data points are colored differently between the two age groups, with ‘Younger’ users represented in red and ‘Older’ users in blue. The blue line represents the linear regression model, showcasing how age influences WhatsApp usage, green data points are used to predict WhatsApp usage for ages 31, 32, 33, 34, and 35, offering valuable understandings into the future trends in WhatsApp usage based on age.
library(readr)
library(dplyr)
library(ggplot2)
# Read the CSV file
data <- read_csv("C:/Users/bhaga/OneDrive/Desktop/new dataset/social media_new.csv")## Rows: 1628 Columns: 40
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (15): City, Current Status, Do you own multiple profiles on Instagram?, ...
## dbl (11): Age, Latitude, Longitude, How many subscriber do you have on youtu...
## num (14): How many followers do you have on Instagram?, How many posts do yo...
##
## 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.# Select the 'Age' and 'Total Social Media Usage' variables
data <- data %>% select(Age, `Total Social Media Usage`)
# Remove any rows with missing values
data <- na.omit(data)
# Convert the 'Age' variable to numeric
data$Age <- as.numeric(data$Age)
# Create a linear regression model
model <- lm(`Total Social Media Usage` ~ Age, data = data)
# Predict the next 5-year value
new_data <- data.frame(Age = c(31, 32, 33, 34, 35))
prediction <- predict(model, newdata = new_data)
# Add a 'Group' column to distinguish older and younger based on age threshold
data <- data %>%
mutate(Group = ifelse(Age > 35, "Older", "Younger"))
# Create a scatter plot with a smoothing line, colored by 'Group'
ggplot(data, aes(x = Age, y = `Total Social Media Usage`, color = Group)) +
geom_point() +
geom_smooth(method = "lm", se = FALSE,color = "blue") +
geom_point(data = new_data, aes(x = Age, y = prediction), color = "yellow", size = 3) +
labs(title = "Age vs. Total Social Media Usage", x = "Age", y = "Total Social Media Usage") +
scale_color_manual(values = c("Younger" = "red", "Older" = "blue")) +
geom_vline(xintercept = 35, linetype = "dashed") # Add a vertical dashed line at age 35## `geom_smooth()` using formula = 'y ~ x'
## a linear regression model to explore the relationship between age and
total social media usage. selecting the ‘Age’ and ‘Total Social Media
Usage’ variables. The core of our analysis is a linear regression model
that models ‘Total Social Media Usage’ based on age. I use this model to
predict the expected usage for the next five years, with ages 31, 32,
33, 34, and 35 included in the new data. data points are color between
‘Younger’ users in red and ‘Older’ users in blue. The blue line
represents the linear regression model, yellow data points are used to
predict social media usage for ages 31, 32, 33, 34, and 35, expected
future trends based on age.
library(readr)
library(dplyr)
library(ggplot2)
# Read the CSV file
data <- read_csv("C:/Users/bhaga/OneDrive/Desktop/new dataset/social media_new.csv")## Rows: 1628 Columns: 40
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (15): City, Current Status, Do you own multiple profiles on Instagram?, ...
## dbl (11): Age, Latitude, Longitude, How many subscriber do you have on youtu...
## num (14): How many followers do you have on Instagram?, How many posts do yo...
##
## 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.# Select the 'Age' and social media usage variables
data <- data %>% select(Age, `Total Facebook Usage`, `Total Social Media Usage`, `Total Instagram Usage`, `Total WhatsApp Usage`)
# Remove any rows with missing values
data <- na.omit(data)
# Convert the 'Age' variable to numeric
data$Age <- as.numeric(data$Age)
# Create linear regression models for each platform and predict the next 5-year values
platforms <- c("Facebook", "Social Media", "Instagram", "WhatsApp")
for (platform in platforms) {
model <- lm(paste0("`Total ", platform, " Usage` ~ Age"), data = data)
new_data <- data.frame(Age = c(31, 32, 33, 34, 35))
prediction <- predict(model, newdata = new_data)
cat("Predicted values for Total", platform, "Usage:", prediction, "\n")
}## Predicted values for Total Facebook Usage: 284.0396 292.0368 300.0339 308.031 316.0281
## Predicted values for Total Social Media Usage: 2002.076 1973.391 1944.706 1916.022 1887.337
## Predicted values for Total Instagram Usage: 615.9642 590.8018 565.6394 540.477 515.3145
## Predicted values for Total WhatsApp Usage: 1102.072 1090.553 1079.033 1067.514 1055.994# Melt the data for easier plotting
data_long <- data %>%
pivot_longer(-Age, names_to = "Platform", values_to = "Usage")
# Add a 'Group' column to distinguish older and younger based on age threshold
data_long <- data_long %>%
mutate(Group = ifelse(Age > 35, "Older", "Younger"))
# Create a single screen with all four scatter plots and linear regression models
ggplot(data_long, aes(x = Age, y = Usage, color = Group)) +
geom_point() +
geom_smooth(method = "lm", se = FALSE,color="blue") +
labs(title = "Age vs. Social Media Usage by Platform", x = "Age", y = "Usage") +
scale_color_manual(values = c("Younger" = "red", "Older" = "blue")) +
geom_vline(xintercept = 35, linetype = "dashed") + # Add a vertical dashed line at age 35
facet_wrap(~Platform, scales = "free_y")## `geom_smooth()` using formula = 'y ~ x'
## This combined chart provides understandings how age influences social
media usage across multiple platforms, including Facebook, Total social
media, Instagram, and WhatsApp, this chart allows us to compare how age
impacts social media usage across various platforms and gain
understandings into expected usage trends as people age.
#thank you mam
ggplot() +
geom_text(aes(x = 0.5, y = 0.5, label = "Thank You Mam", size = 10)) +
theme_void()