instagram_posts_analysis.r

library(tidyverse)

d <- read_csv("top_posts_instagram_12meses_abril2021.csv")

top_posts <- d %>%
  arrange(desc(`Total Interactions`)) %>%
  head(1000)


top_profiles <- d %>%
  group_by(`User Name`) %>%
  mutate(n_posts = n(), interacoes = sum(`Total Interactions`), comentarios = sum(Comments), likes = sum(Likes), media_overperforming = round(mean(`Overperforming Score`),2)) %>%
  select(`User Name`, Account, n_posts, interacoes, comentarios, likes, media_overperforming) %>%
  distinct(`User Name`, .keep_all = T) %>%
  mutate(tx_engajamento = round(sum(interacoes / n_posts), 2)) %>%
  arrange(desc(tx_engajamento))