report
### https://rstudio-pubs-static.s3.amazonaws.com/595002_2d1617098c8c44b494bc2ec97018a82b.html
setwd("C:/Users/mvx13/OneDrive - Texas State University/0_Codes/2023/academicTwitteR/walkablecities")
library(readxl)
dat= read_xlsx("#15minutecities_03252023.xlsx")
dim(dat)
## [1] 48401 30
library(rtweet)
library(tidyverse)
hashtag_pat <- "#[a-zA-Z0-9_-ー\\.]+"
hashtag <- str_extract_all(dat$text, hashtag_pat)
hashtag_word <- unlist(hashtag)
hashtag_word <- tolower(hashtag_word)
hashtag_word <- gsub("[[:punct:]ー]", "", hashtag_word)
hashtag_count <- table(hashtag_word)
top_20_freqs <- sort(hashtag_count, decreasing = TRUE)[1:20]
top_20_freqs
## hashtag_word
## 15minutecities oxford wef agenda2030
## 28437 3731 2202 1874
## greatreset 15minutecity 15minuteprisons climatescam
## 1411 1370 1284 1224
## digitalid nwo 15minutecit cbdc
## 1143 1134 916 804
## ltns newworldorder klausschwab ulez
## 786 671 555 543
## diedsuddenly socialcreditsystem yeg smartcities
## 523 451 425 396
hashtag_word <- hashtag_word[!str_detect(hashtag_word, "15minutecities")]
hashtag_word <- hashtag_word[!str_detect(hashtag_word, "15minutecity")]
hashtag_word <- hashtag_word[!str_detect(hashtag_word, "15minutecit")]
hashtag_word <- hashtag_word[!str_detect(hashtag_word, "smartcities")]
as.data.frame(hashtag_word) %>%
count(hashtag_word, sort = TRUE) %>%
mutate(hashtag_word = reorder(hashtag_word, n)) %>%
top_n(100) %>%
ggplot(aes(x = hashtag_word, y = n)) +
geom_col() +
coord_flip() +theme_bw()+
labs(x = "Count",
y = "Hashtag",
title = "Top 20 Popular Hashtags along with #15minutecities")
