Wordclouds:

wc(HC)

Next up maps. Some work better than others…..

map_tweets(HC)

map_gen_w(HC)

map_gen_s(HC)
## 'data.frame':    512600 obs. of  11 variables:
##  $ text         : Factor w/ 966631 levels "","'''moderate''' https://t.co/K6YUR3J7R1",..: 659713 720794 345588 726622 802252 149175 684671 743778 808083 726255 ...
##  $ id_str       : Factor w/ 1987277 levels "","000086513b2042b6",..: 139740 139738 139741 139736 139752 139753 139755 139761 139764 139766 ...
##  $ created_at   : Factor w/ 97435 levels "","_Kushington",..: 121 121 121 121 122 122 122 122 122 122 ...
##  $ screen_name  : Factor w/ 504602 levels "","___________2016",..: 16732 34752 54385 473245 39610 44769 170733 454476 395520 106517 ...
##  $ place_lat    : num  NA NA NA NA NA NA NA NA NA NA ...
##  $ place_lon    : Factor w/ 4671 levels "","-0.010624",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ lat          : Factor w/ 665 levels "","-0.2021432",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ lon          : Factor w/ 662 levels "","-0.0980547",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ country_code : Factor w/ 121 levels "","AE","AL","AQ",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ retweeted    : Factor w/ 3827 levels "","0","All about entertainment",..: 5 5 5 5 5 5 5 5 5 5 ...
##  $ retweet_count: Factor w/ 7491 levels "","0","715195860594720768",..: 2 2 2 2 2 2 2 2 2 2 ...

state_mp_cnt(HC)
## [1] "two"
## [1] "three"

Social Networks:

# TBD

Sentiment Analysis:

HC_p<- read.csv("HC_polarity_e.csv")
plot_polarity(HC_p)