Visualizing US Youtube Trending Videos 2017
Data Explanation
Objective
This dataset comes from United States Youtube Trending Videos in 2017. There are 13.400 data from 16 category videos. This data consist of trending date, video title, channel title, views, likes, comment, dislikes, etc.
Why?
We have a lot of information of this dataset about some channel title with high views, likes, comment, and so on. But, we are not able to know what kind of videos which get a lot of view, likes, and comment. By aggregating and visualizing the data properly, we would understand the data better than before. That’s why, visualization is very important to deliver information and get more understandings of the data.
Data Preparation
data <- read.csv("USvideos.csv")
rmarkdown::paged_table(data)str(data)## 'data.frame': 13400 obs. of 12 variables:
## $ trending_date : chr "17.14.11" "17.14.11" "17.14.11" "17.14.11" ...
## $ title : chr "WE WANT TO TALK ABOUT OUR MARRIAGE" "The Trump Presidency: Last Week Tonight with John Oliver (HBO)" "Racist Superman | Rudy Mancuso, King Bach & Lele Pons" "Nickelback Lyrics: Real or Fake?" ...
## $ channel_title : chr "CaseyNeistat" "LastWeekTonight" "Rudy Mancuso" "Good Mythical Morning" ...
## $ category_id : int 22 24 23 24 24 28 24 28 1 25 ...
## $ publish_time : chr "2017-11-13T17:13:01.000Z" "2017-11-13T07:30:00.000Z" "2017-11-12T19:05:24.000Z" "2017-11-13T11:00:04.000Z" ...
## $ views : int 748374 2418783 3191434 343168 2095731 119180 2103417 817732 826059 256426 ...
## $ likes : int 57527 97185 146033 10172 132235 9763 15993 23663 3543 12654 ...
## $ dislikes : int 2966 6146 5339 666 1989 511 2445 778 119 1363 ...
## $ comment_count : int 15954 12703 8181 2146 17518 1434 1970 3432 340 2368 ...
## $ comments_disabled : logi FALSE FALSE FALSE FALSE FALSE FALSE ...
## $ ratings_disabled : logi FALSE FALSE FALSE FALSE FALSE FALSE ...
## $ video_error_or_removed: logi FALSE FALSE FALSE FALSE FALSE FALSE ...Result: We have to notice that those (channel_title, publish_time, trending_date, and category_id) columns have incorrect data type. So we have to make it right by changing the type of the data.
Exploratory Data Analysis
Changing type of data
# ubah isi kolom
data$category_id <- sapply(as.character(data$category_id), switch,
"1" = "Film and Animation",
"2" = "Autos and Vehicles",
"10" = "Music",
"15" = "Pets and Animals",
"17" = "Sports",
"19" = "Travel and Events",
"20" = "Gaming",
"22" = "People and Blogs",
"23" = "Comedy",
"24" = "Entertainment",
"25" = "News and Politics",
"26" = "Howto and Style",
"27" = "Education",
"28" = "Science and Technology",
"29" = "Nonprofit and Activism",
"43" = "Shows")
data$category_id <- as.factor(data$category_id)
library(lubridate)
data$trending_date <- ydm(data$trending_date)
data$publish_time <- ymd_hms(data$publish_time, tz = "America/New_York")## Date in ISO8601 format; converting timezone from UTC to "America/New_York".Adding Some New Columns (Likes Rate, Dislike Rate, Comment Rate)
data$likesp <- data$likes/data$views
data$dislikesp <- data$dislikes/data$views
data$commentp <- data$comment_count/data$viewsTop 5 Videos Based on Likes Rate
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, uniontop_10_video <- aggregate(likesp~title, data, mean)
top_10_video <- head(top_10_video[order(top_10_video$likesp, decreasing = T),],10)
top_10_video## title
## 1277 Idol EXPOSES Dark Side of KPOP | STORYTIME experiences with SCANDALS, Slave Contracts and more
## 1045 Harry Styles - Kiwi (live in studio)
## 982 GOALS GOALS GOALS
## 1110 How Do Machines Learn?
## 2598 THINGS THAT ARE LOWER
## 588 COMING OUT TO MY LESBIAN MOMS
## 441 BTS (‘¡©’Ä㓠ΑÉã‘ܬ) 'MIC Drop (Steve Aoki Remix)' Official Teaser
## 1594 Liam Payne - Bedroom Floor (Live Acoustic)
## 2609 This Is What I'm Wearing Right Now
## 1319 Interlude III - original song | Tessa Violet
## likesp
## 1277 0.2281817
## 1045 0.1915195
## 982 0.1834375
## 1110 0.1759662
## 2598 0.1740575
## 588 0.1709072
## 441 0.1666532
## 1594 0.1654369
## 2609 0.1624418
## 1319 0.1586368Visualizing the Top 10 Videos
library(ggplot2)
plot_top_10_video <- ggplot(top_10_video, aes(x=likesp, y=reorder(title, likesp)))+
geom_col(aes(fill=likesp), show.legend = F)+
scale_fill_gradient(low = "black", high = "aquamarine")+
#geom_vline(xintercept = mean(data$likesp),
#col="green",
#linetype=2,
#lwd=1)+
geom_label(data = top_10_video, mapping = aes(label=round(likesp, 2)))+
labs(title = "Top 10 Videos ",
x = "Likes rate",
y = "Title",
caption = "Source: Youtube US Trending")
plot_top_10_video
Result: We can see that video title “Idol EXPOSES Dark Side of KPOP | STORYTIME ….” gets the highest likes rate video.
Top 10 Channel Youtube Based on Likes rate
top_10_channel <- aggregate(likesp~channel_title, data, sum)
top_10_channel <- head(top_10_channel[order(top_10_channel$likesp, decreasing = T),],10)
top_10_channel## channel_title likesp
## 1106 SMTOWN 4.230463
## 558 IISuperwomanII 3.893953
## 273 ConnorFranta 3.678392
## 1285 Tom Scott 3.102886
## 582 jacksfilms 3.043967
## 1348 vlogbrothers 2.979222
## 1383 William Osman 2.894096
## 766 Marques Brownlee 2.880029
## 771 Marzia 2.879472
## 580 Jackie Aina 2.856786Visualizing the Top 10 Channel
plot_top_10_channel <- ggplot(top_10_channel, aes(x=likesp, y=reorder(channel_title, likesp)))+
geom_col(aes(fill=likesp), show.legend = F)+
scale_fill_gradient(low = "royal blue", high = "aquamarine")+
#geom_vline(xintercept = mean(data$likesp),
#col="green",
#linetype=2,
#lwd=1)+
geom_label(data = top_10_channel, mapping = aes(label=round(likesp, 2)))+
labs(title = "Top 10 Channel Based on Likes Rate",
x = "Likes Rate",
y = "Channel Title",
caption = "Source: Youtube US Trending")
plot_top_10_channel
Result: Channels with the highest likes rate were SMTOWN, ||Superwoman||, ConnorFranta, and so on.
Top 10 Category Based on Total Views
top_category <- aggregate(views ~ category_id, data, sum)
top_category <- top_category[order(top_category$views, decreasing = TRUE),]
top_category## category_id views
## 8 Music 5479488307
## 4 Entertainment 4781000701
## 2 Comedy 1373174698
## 5 Film and Animation 1066571908
## 7 Howto and Style 918635366
## 11 People and Blogs 794253563
## 13 Science and Technology 598040232
## 15 Sports 464583585
## 9 News and Politics 314142992
## 3 Education 260789748
## 12 Pets and Animals 179846802
## 6 Gaming 158951143
## 1 Autos and Vehicles 89924854
## 16 Travel and Events 61874890
## 14 Shows 1751446
## 10 Nonprofit and Activism 383367Visualizing Top 10 Category
plot_top_category <- ggplot(top_category, aes(x=views, y=reorder(category_id, views)))+
geom_col(aes(fill=views), show.legend = T)+
scale_fill_gradient(low = "black", high = "aquamarine")+
labs(title = "Top 10 Category Based on Total Views",
x = "Total Views",
y = "Channel Title",
caption = "Source: Youtube US Trending")
plot_top_category
Result: Based on the plot above, we can see that Music is the most views of category in US Youtube Trending Videos 2017. Therefore, we can find out which channels are the biggest contributors to Music views by aggregating the data.
#Filtering data only Music category
music <- data %>%
filter(category_id=="Music")
#Selecting channel_title and views columns
music <- music %>%
select(channel_title, views)
#Aggregating data to ordering the top 10
music <- aggregate(views~channel_title, music, sum)
top_10_music <- head(music[order(music$views, decreasing = T),],10)
top_10_music## channel_title views
## 149 LuisFonsiVEVO 534738794
## 91 GEazyMusicVEVO 415888915
## 74 Ed Sheeran 400504946
## 77 EminemVEVO 287435495
## 123 jypentertainment 276291969
## 125 KatyPerryVEVO 273333649
## 237 TaylorSwiftVEVO 244182424
## 108 ibighit 224009476
## 39 Bruno Mars 213126073
## 65 DemiLovatoVEVO 174572450Visualizing Top 10 Channel in Music Category
plot_top_10_music <- ggplot(top_10_music, aes(x=views, y=reorder(channel_title, views)))+
geom_col(aes(fill=views), show.legend = F)+
scale_fill_gradient(low = "black", high = "aquamarine")+
labs(title = "Top 10 Channel in Music Category Based on Total Views",
x = "Total Views",
y = "Channel Title",
caption = "Source: Youtube US Trending")
plot_top_10_music
Result: LuisFonsiVEVO, GEazyMusicVEVO, and Ed Sheeran were the top three of music videos with the most viewed in US Trending Youtube 2017.
Conclusion
From the two first plot, we can see that Korean Youtube channel and video get the highest likes rate in US Youtube Trending Video 2017. If we do further analysis, we would find out that KPOP things is getting popular at the last decade with some artists or musicians such as BlackPink, BTS, etc. Then, in the US Youtube trending 2017, music got the most viewed category than the others. So we can conclude that US residents loved listening and watching music videos on Youtube in 2017.