supermercado_twitter.R

library(dplyr)
library(rtweet)
library(ggplot2)
library(chron) 

supermercado_busca <- search_tweets("\"estou no supermercado\"", n = 18000,
                       retryonratelimit = T,
                       include_rts = F)

supermercado <- supermercado_busca
supermercado <- supermercado %>%
  filter(lang == "pt")

# regulariza o formato da data do tweet, corrige para fuso certo
supermercado$created_at <- as.POSIXct(strptime(supermercado$created_at, "%Y-%m-%d %H:%M:%S"))
supermercado$created_at <- supermercado$created_at - hours(3)
supermercado$dia <- as.POSIXct(strptime(supermercado$created_at, "%Y-%m-%d"))

# cria coluna com minuto arredondado
supermercado$min_redondo <- round(supermercado$created_at, units = "hours")
supermercado$horario_tweet <- times(strftime(supermercado$min_redondo,"%H:%M:%S"))

contagem <-  supermercado %>%
  group_by(horario_tweet) %>%
  count() %>%
  ungroup() %>%
  mutate(percentual = round((n/sum(n))*100, digits = 1))

contagem$horario_tweet <- factor(as.character(contagem$horario_tweet),
                                 levels = c("00:00:00", "01:00:00", "02:00:00", "03:00:00",
                                            "04:00:00", "05:00:00", "06:00:00", "07:00:00", 
                                            "08:00:00", "09:00:00", "10:00:00", "11:00:00",
                                            "12:00:00", "13:00:00", "14:00:00", "15:00:00", 
                                            "16:00:00", "17:00:00", "18:00:00", "19:00:00", 
                                            "20:00:00", "21:00:00", "22:00:00", "23:00:00"),
                                 labels = c(paste0(seq(0, 23, 1), "h")))

contagem %>%
  ggplot(aes(horario_tweet, percentual)) + 
  geom_bar(stat = "identity") +
  scale_x_discrete(breaks = c(paste0(seq(0, 22, 2), "h"))) +
  #scale_y_continuous(limits = c(0,9), breaks = seq(0,9,1)) +
  theme_minimal() +
  theme(plot.title = element_text(hjust = 0.5, size = 12),
        plot.caption = element_text(hjust = 0.5, size = 9),
        axis.title.x = element_text(hjust = 0.5, size = 10),
        axis.title.y = element_text(hjust = 0.5, size = 10)) +
  labs(title = "Horários de tweets que contêm \"supermercado+estou\"",
       caption = "Fonte: 21 tweets em português postados entre os\ndias 21 e 27 de março (coletados com o pacote rtweet)",
       x = "Horário da postagem (Brasília)", y = "Percentual do total de tweets")
ggsave("supermercado.jpeg", dpi = 300, width = 6, height = 4)