library(readxl)
library(plyr)
before debate
before <- read_xlsx("C:/Users/jm/Documents/sawi/5000 samples/all.xlsx", sheet = "before")
table(before$tweet_type)
##
## original quote reply retweet
## 1323 311 280 3082
after debate
after <- read_xlsx("C:/Users/jm/Documents/sawi/5000 samples/all.xlsx", sheet = "after")
table(after$tweet_type)
##
## original quote reply retweet
## 544 253 251 3955
summary(after[,c(7,11,17:19,21, 23)])
## favorite_count retweet_count user_favourites_count
## Min. : 0.0000 Min. : 0 Min. : 0
## 1st Qu.: 0.0000 1st Qu.: 5 1st Qu.: 1462
## Median : 0.0000 Median : 409 Median : 6737
## Mean : 0.4973 Mean : 7720 Mean : 22065
## 3rd Qu.: 0.0000 3rd Qu.: 6472 3rd Qu.: 23808
## Max. :932.0000 Max. :560967 Max. :536432
##
## user_followers_count user_friends_count user_statuses_count
## Min. : 0 Min. : 0 Min. : 2
## 1st Qu.: 158 1st Qu.: 222 1st Qu.: 3792
## Median : 511 Median : 568 Median : 14696
## Mean : 3551 Mean : 1863 Mean : 44314
## 3rd Qu.: 1655 3rd Qu.: 1685 3rd Qu.: 46042
## Max. :3116371 Max. :149790 Max. :7794240
## NA's :1
## user_verified
## Mode :logical
## FALSE:4940
## TRUE :62
## NA's :1
##
##
##
during a
during_a <- read_xlsx("C:/Users/jm/Documents/sawi/5000 samples/all.xlsx", sheet = "during a")
table(during_a$tweet_type)
##
## original quote reply retweet
## 1403 206 411 2975
summary(during_a[,c(7,11,17:19,21, 23)])
## favorite_count retweet_count user_favourites_count
## Min. : 0.0000 Min. : 0 Min. : 0
## 1st Qu.: 0.0000 1st Qu.: 0 1st Qu.: 795
## Median : 0.0000 Median : 33 Median : 3866
## Mean : 0.8396 Mean : 5483 Mean : 14739
## 3rd Qu.: 0.0000 3rd Qu.: 2708 3rd Qu.: 14588
## Max. :745.0000 Max. :560984 Max. :526263
##
## user_followers_count user_friends_count user_statuses_count
## Min. : 0 Min. : 0.0 Min. : 1
## 1st Qu.: 121 1st Qu.: 200.5 1st Qu.: 1860
## Median : 346 Median : 450.0 Median : 7596
## Mean : 5276 Mean : 1371.2 Mean : 25815
## 3rd Qu.: 1040 3rd Qu.: 1077.5 3rd Qu.: 25848
## Max. :4659697 Max. :561152.0 Max. :1467014
## NA's :4
## user_verified
## Mode :logical
## FALSE:4917
## TRUE :74
## NA's :4
##
##
##
during b
during_b <- read_xlsx("C:/Users/jm/Documents/sawi/5000 samples/all.xlsx", sheet = "during b")
table(during_b$tweet_type)
##
## original quote reply retweet
## 1396 182 414 3008
summary(during_b[,c(7,11,17:19,21,23)])
## favorite_count retweet_count user_favourites_count
## Min. : 0.0000 Min. : 0 Min. : 0
## 1st Qu.: 0.0000 1st Qu.: 0 1st Qu.: 749
## Median : 0.0000 Median : 36 Median : 3716
## Mean : 0.4488 Mean : 5745 Mean : 15208
## 3rd Qu.: 0.0000 3rd Qu.: 2920 3rd Qu.: 14514
## Max. :326.0000 Max. :560983 Max. :1258107
##
## user_followers_count user_friends_count user_statuses_count
## Min. : 0.0 Min. : 0 Min. : 1
## 1st Qu.: 113.0 1st Qu.: 201 1st Qu.: 1910
## Median : 345.0 Median : 464 Median : 7478
## Mean : 3426.1 Mean : 1319 Mean : 25675
## 3rd Qu.: 992.5 3rd Qu.: 1087 3rd Qu.: 25141
## Max. :2706149.0 Max. :561152 Max. :1173411
## NA's :2
## user_verified
## Mode :logical
## FALSE:4933
## TRUE :65
## NA's :2
##
##
##
during c
during_c <- read_xlsx("C:/Users/jm/Documents/sawi/5000 samples/all.xlsx", sheet = "during c")
table(during_c$tweet_type)
##
## original quote reply retweet
## 1447 179 437 2936
summary(during_c[,c(7,11,17:19,21, 23)])
## favorite_count retweet_count user_favourites_count
## Min. : 0.0000 Min. : 0 Min. : 0
## 1st Qu.: 0.0000 1st Qu.: 0 1st Qu.: 797
## Median : 0.0000 Median : 23 Median : 3901
## Mean : 0.9164 Mean : 5824 Mean : 15690
## 3rd Qu.: 0.0000 3rd Qu.: 2452 3rd Qu.: 14844
## Max. :463.0000 Max. :560985 Max. :875227
##
## user_followers_count user_friends_count user_statuses_count
## Min. : 0 Min. : 0 Min. : 1
## 1st Qu.: 116 1st Qu.: 198 1st Qu.: 1830
## Median : 351 Median : 456 Median : 7594
## Mean : 7103 Mean : 1226 Mean : 26613
## 3rd Qu.: 1022 3rd Qu.: 1066 3rd Qu.: 26243
## Max. :19633845 Max. :561153 Max. :1186831
## NA's :2
## user_verified
## Mode :logical
## FALSE:4929
## TRUE :68
## NA's :2
##
##
##