Data Dive Week 3
2025-02-03
library(tidyverse)## Warning: package 'tidyverse' was built under R version 4.3.3## Warning: package 'ggplot2' was built under R version 4.3.3## Warning: package 'tibble' was built under R version 4.3.3## Warning: package 'tidyr' was built under R version 4.3.3## Warning: package 'readr' was built under R version 4.3.3## Warning: package 'purrr' was built under R version 4.3.3## Warning: package 'dplyr' was built under R version 4.3.3## Warning: package 'stringr' was built under R version 4.3.3## Warning: package 'forcats' was built under R version 4.3.3## Warning: package 'lubridate' was built under R version 4.3.3## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ 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(dplyr)
library(ggplot2)
data <-read.csv("social_media_entertainment_data.csv")
df_1 <- data %>% filter(Country == "UsA")platform_time <- data %>%
group_by(Primary.Platform) %>%
summarise(Average_Time_Per_Platform = mean(Daily.Social.Media.Time..hrs.), User_Count = n())
platform_time## # A tibble: 5 × 3
## Primary.Platform Average_Time_Per_Platform User_Count
## <chr> <dbl> <int>
## 1 Facebook 4.26 59936
## 2 Instagram 4.25 59721
## 3 TikTok 4.25 60301
## 4 Twitter 4.25 60285
## 5 YouTube 4.27 59757ggplot(platform_time, aes(x = reorder(Primary.Platform, -Average_Time_Per_Platform), y = Average_Time_Per_Platform, fill = Primary.Platform)) +
geom_col() +
labs(title = "Average Daily Social Media Time by Platform",
x = "Social Media Platform",
y = "Average Time Spent (hrs)") +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
Analysis:
The data suggests that users split their time evenly across different platforms
Equal distribution of time could indicate that no single platform dominates users’ daily routines
The data also suggests that TikTok has the most users indicating its popularity
Hypothesis: Facebook may have the lowest amount of users which may be a cause of its engagement strategies.
Average_Social_Media_Time_Per_Occupation <- data %>%
group_by(Occupation) %>%
summarise(
Average_Social_Media_Time = mean(Daily.Social.Media.Time..hrs.),
Employee_Count = n()
)
Average_Social_Media_Time_Per_Occupation## # A tibble: 4 × 3
## Occupation Average_Social_Media_Time Employee_Count
## <chr> <dbl> <int>
## 1 Professional 4.26 75332
## 2 Retired 4.25 74835
## 3 Student 4.27 74875
## 4 Unemployed 4.25 74958ggplot(Average_Social_Media_Time_Per_Occupation, aes(x = reorder(Occupation, -Average_Social_Media_Time), y = Average_Social_Media_Time, fill = Occupation)) +
geom_col() +
labs(title = "Average Social Media Time Per Occupation",
x = "Occupation",
y = "Average Social Media Time (hrs)") +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
Insights:
Students spend the most time on social media (4.27 hrs), which could be due to the younger age group being more attracted to digital platforms
Retired and Unemployed people have very similar consumption times which may indicate that social media helps them stay connected to the world.
The average social media time between all groups is very similar suggesting that occupation does not significantly affect consumption time.
Hypothesis: Students may use social media more due to their age and ability to use technology freely.
data <- data %>%
mutate(Category = cut(Internet.Speed..Mbps.,
breaks = c(0, 25, 50, 75, 100),
labels = c("Very Slow", "Slow", "Moderate", "Fast"),
include.lowest = TRUE))
internet_speed_groups <- data %>%
group_by(Category) %>%
summarise(AverageTime = mean(Time.Spent.in.Online.Communities..hrs., na.rm = TRUE),
Users = n())
internet_speed_groups## # A tibble: 4 × 3
## Category AverageTime Users
## <fct> <dbl> <int>
## 1 Very Slow 2.00 63128
## 2 Slow 2.00 79082
## 3 Moderate 2.01 79022
## 4 Fast 2.00 78768ggplot(internet_speed_groups, aes(x = Category, y = AverageTime, fill = Category)) +
geom_col() +
labs(title = "Time Spent in Online Communities by Internet Speed Category",
x = "Internet Speed Category",
y = "Average Time Spent (hrs)")
Insights:
Regardless of internet speeds, the average time spent in online communities remains similar throughout the categories. This suggests that internet speeds do not influence it as much.
The Very Slow category has the lowest numbers of users, indicating that it is uncommon to have lower speeds than 25 Mbps.
Hypothesis: People with very slow speeds might struggle with engagement, for example by having buffering issues. This can indirectly cause them to be online for more time than users with faster speeds.
Data Frame
combination_groups <- data %>%
group_by(Occupation, Primary.Platform) %>%
summarise(n = n()) %>%
ungroup()## `summarise()` has grouped output by 'Occupation'. You can override using the
## `.groups` argument.all_combinations <- expand.grid(
Occupation = unique(data$Occupation),
Primary.Platform = unique(data$Primary.Platform)
)
missing_combinations <- anti_join(all_combinations, combination_groups, by = c("Occupation", "Primary.Platform"))
print(missing_combinations)## [1] Occupation Primary.Platform
## <0 rows> (or 0-length row.names)print(combination_groups)## # A tibble: 20 × 3
## Occupation Primary.Platform n
## <chr> <chr> <int>
## 1 Professional Facebook 15191
## 2 Professional Instagram 14899
## 3 Professional TikTok 15097
## 4 Professional Twitter 15205
## 5 Professional YouTube 14940
## 6 Retired Facebook 14947
## 7 Retired Instagram 14767
## 8 Retired TikTok 15002
## 9 Retired Twitter 15044
## 10 Retired YouTube 15075
## 11 Student Facebook 14906
## 12 Student Instagram 15231
## 13 Student TikTok 15063
## 14 Student Twitter 14957
## 15 Student YouTube 14718
## 16 Unemployed Facebook 14892
## 17 Unemployed Instagram 14824
## 18 Unemployed TikTok 15139
## 19 Unemployed Twitter 15079
## 20 Unemployed YouTube 15024ggplot(combination_groups, aes(x = Occupation, y = Primary.Platform, fill = n)) +
geom_tile() +
scale_fill_gradient(low = "white", high = "blue") +
labs(title = "Heatmap of Occupation and Primary.Platform Combinations",
x = "Occupation",
y = "Primary Platform",
fill = "Count")
Insights:
The most common combination was “Student” and “Instagram”, indicating that it may be preferred due to its social and entertainment contents.
The least common combination was “Student” and “Youtube” which indicates that students don’t tend to use Youtube as commonly as other platforms. This could be due to Youtube not being as social or entertaining as say, Instagram or Tiktok.
Instagram and Facebook both show relatively high usage across most occupations indicating that they are popular for personal engagement.
Tiktok shows high usage across all occupations suggesting a growing influence.