breastfeeding text analysis final project

library(rtweet)
library(tidyverse)

── Attaching packages ─────────────────────── tidyverse 1.2.1 ──
✔ ggplot2 3.1.0     ✔ purrr   0.2.5
✔ tibble  2.0.0     ✔ dplyr   0.7.8
✔ tidyr   0.8.2     ✔ stringr 1.3.1
✔ readr   1.3.1     ✔ forcats 0.3.0
── Conflicts ────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter()  masks stats::filter()
✖ purrr::flatten() masks rtweet::flatten()
✖ dplyr::lag()     masks stats::lag()

library(tidytext)
library(DT)
library(plotly)

Attaching package: ‘plotly’

The following object is masked from ‘package:ggplot2’:

    last_plot

The following object is masked from ‘package:stats’:

    filter

The following object is masked from ‘package:graphics’:

    layout

library(wordcloud2)

breastfeeding_tweets <- get_timeline("@BreastfeedingM
", n = 5000)

breastfeeding_words <- breastfeeding_tweets %>% 
  unnest_tokens(word, text) %>% 
  select(screen_name, word)

breastfeeding_words %>%
  count(word, sort = T)

breastfeeding_words %>% 
  anti_join(get_stopwords()) %>% 
  count(word, sort = T)

Joining, by = "word"

breastfeeding_words %>% 
  anti_join(get_stopwords()) %>% 
  filter(!word == "https",
         !word == "t.co") %>%
  count(word, sort = T)

Joining, by = "word"

breastfeeding_words %>% 
  anti_join(get_stopwords()) %>% 
  filter(!word == "https",
         !word == "t.co") %>%
  count(word, sort = T) %>%
  top_n(200) %>%
  wordcloud2(size = 1)

Joining, by = "word"
Selecting by n

bing <- get_sentiments("bing")
bing

breastfeeding_words %>% 
  inner_join(bing) %>% 
  count(word, sentiment, sort = TRUE)

Joining, by = "word"

breastfeeding_words %>% 
  inner_join(bing) %>% 
  filter(!word == "breastfeeding") %>%
  count(word, sentiment, sort = TRUE)%>%
  group_by(sentiment) %>%
  top_n(10) %>%
  ungroup() %>%
  mutate(word = reorder(word, n)) %>%
  ggplot(aes(word, n, fill = sentiment)) +
  geom_col(show.legend = FALSE) +
  facet_wrap(vars(sentiment), scales = "free") +
  labs(y = "breastfeeding words positive vs negative ",
       x = NULL) +
  coord_flip() +
  theme_minimal()

Joining, by = "word"
Selecting by n

breastfeeding_words %>% 
  inner_join(nrc) %>% 
  filter(!word == "breast") %>%
  count(word, sentiment, sort = TRUE)%>%
  group_by(sentiment) %>%
  top_n(5) %>%
  ungroup() %>%
  mutate(word = reorder(word, n)) %>%
  ggplot(aes(word, n, fill = sentiment)) +
  geom_col(show.legend = FALSE) +
  facet_wrap(vars(sentiment), scales = "free") +
  labs(y = "Breastfeeding verbage",
       x = NULL) +
  coord_flip() +
  theme_minimal()

Joining, by = "word"
Selecting by n

breastfeeding_tweets %>%
  select(text) %>%                                                 # this selects just the text of the tweets
  unnest_tokens(words, text, token = "ngrams", n = 2) %>% 
  separate(words, c("word1", "word2"), sep = " ") %>%          # separate them temporarily
  filter(!word1 %in% stop_words$word) %>%                      # remove if first word is a stop word
  filter(!word2 %in% stop_words$word) %>%                      # remove if second word is a stop word   
  unite(words, word1, word2, sep = " ")                        # put them back together

NA

remove_words = c("https", "t.co")

breastfeeding_tweets %>%
  select(text) %>%                                                 
  unnest_tokens(words, text, token = "ngrams", n = 2) %>% 
  separate(words, c("word1", "word2"), sep = " ") %>%          # separate them temporarily
  filter(!word1 %in% stop_words$word) %>%                      # remove if first word is a stop word
  filter(!word2 %in% stop_words$word) %>%                      # remove if second word is a stop word   
  filter(!word1 %in% remove_words) %>%                         # these two lines remove our remove_words
  filter(!word2 %in% remove_words) %>%                         
  unite(words, word1, word2, sep = " ")                        # put them back together

remove_words = c("https", "t.co")

breastfeeding_tweets %>%
  select(text) %>%                                                 
  unnest_tokens(words, text, token = "ngrams", n = 2) %>% 
  separate(words, c("word1", "word2"), sep = " ") %>%          # separate them temporarily
  filter(!word1 %in% stop_words$word) %>%                      # remove if first word is a stop word
  filter(!word2 %in% stop_words$word) %>%                      # remove if second word is a stop word   
  filter(!word1 %in% remove_words) %>%                         # these two lines remove our remove_words
  filter(!word2 %in% remove_words) %>%                         
  unite(words, word1, word2, sep = " ") -> breastfeeding_bigrams                       # put them back together

breastfeeding_bigrams %>% 
  count(words, sort = T)

breastfeeding_bigrams %>% 
  count(words, sort = T) %>%
  top_n(100) %>%
  wordcloud2(size = .5)

Selecting by n

first_word <- c("wine", "breastfeeding")                                  # these need to be lowercase

breastfeeding_bigrams %>%             
  count(words, sort = TRUE) %>%
  separate(words, c("word1", "word2"), sep = " ") %>%       # separate the two words
  filter(word1 %in% first_word) %>%                          # find first words from our list
  count(word1, word2, wt = n, sort = TRUE) %>% 
  rename(total = nn)

first_word <- c("benifits", "breastfeeding")                                  # these need to be lowercase

breastfeeding_bigrams %>%             
  count(words, sort = TRUE) %>%
  separate(words, c("word1", "word2"), sep = " ") %>%       # separate the two words
  filter(word1 %in% first_word) %>%                          # find first words from our list
  count(word1, word2, wt = n, sort = TRUE) %>% 
  rename(total = nn) %>%
  mutate(word2 = factor(word2, levels = rev(unique(word2)))) %>%     # put the words in order
  group_by(word1) %>% 
  top_n(5) %>% 
  ggplot(aes(word2, total, fill = word1)) +                          #
  scale_fill_viridis_d() +                                           # set the color palette
  geom_col(show.legend = FALSE) +
  labs(x = NULL, y = NULL, title = "Breastfeeding") +
  facet_wrap(~word1, scales = "free") +
  coord_flip()

Selecting by total

breastfeeding_words %>%
  mutate(word_length = nchar(word)) %>% 
  ggplot(aes(word_length)) +
  geom_histogram(binwidth = 1)