R Notebook

library(tidyverse)
library(DT)
library(tidytext)        # package for text analysis
library(readxl)          # reads excel files, the format I used for the data

1. Read in the text and unnest the words.

manifestos <- read_excel("manifestos .xlsx")

manifestos

manifestos_words <- manifestos %>%
  unnest_tokens(word, text)

manifestos_words

NA

Here I read in the text and unnested the words.

2. Generate a table that includes both lexical diversity and density, and the total number of words, of each document.

manifestos_words %>% 
  group_by(author) %>% 
  summarise(num_words = n(),
            lex_diversity = n_distinct(word), 
            lex_density = n_distinct(word)/n())

This is a table showing lexical diversity and density, and the total number of words, of each document.

3. Generate a table with the mean word length of each document.

manifestos_words %>%
  group_by(author) %>% 
  mutate(word_length = nchar(word)) %>% 
  summarize(mean_word_length = mean(word_length)) %>% 
  arrange(-mean_word_length)

This is a table showing the mean word length of each document.

4. Generate a graph with mini histograms of each document’s word lengths.

manifestos_words %>%
  mutate(word_length = nchar(word)) %>% 
  ggplot(aes(word_length)) +
  geom_histogram(binwidth = 1) +
  facet_wrap(vars(author), scales = "free_y") +
  labs(title = "Word Lengths by Document")

These are histograms showing the mean word length in each document.

5. Remove stop words and then create a graph with the most common words in each document.

manifestos_words %>%
  anti_join(stop_words) %>% 
  group_by(author) %>% 
  count(word, sort = T) %>%
  top_n(5) %>% 
  ungroup() %>% 
  mutate(word = reorder(word, n)) %>%
  ggplot(aes(word, n, fill = author)) +
  geom_col(show.legend = FALSE) +
  labs(x = NULL, y = "Most common words") +
  facet_wrap(vars(author), scales = "free") +
  scale_fill_viridis_d() +
  theme_minimal() +
  coord_flip()

Joining, by = "word"
Selecting by n

These are graphs showing the most common words in each document, not including stop words.

6. Calculate tf-idfs and create a graph of the words with the highest tf-idfs in each document.

manifestos_word_counts <- suicide_notes %>%             # This counts each word per author
  unnest_tokens(word, text) %>%
  count(author, word, sort = TRUE) 

total_words <- manifestos_word_counts %>%               # This counts total words per author
  group_by(author) %>% 
  summarize(total = sum(n))

manifestos_word_counts <- left_join(manifestos_word_counts, total_words)    # Joins the two

Joining, by = "author"

manifestos_tf_idf <- manifestos_word_counts %>%             # Calculates tf-idf
  bind_tf_idf(word, author, n)

manifestos_tf_idf %>%                                   # Displays it
  arrange(-tf_idf)                          

NA

This shows the calculation of the tf-idfs.

manifestos_tf_idf %>%
  arrange(-tf_idf) %>%
  mutate(word = factor(word, levels = rev(unique(word)))) %>% 
  group_by(author) %>% 
  top_n(5) %>% 
  ggplot(aes(word, tf_idf, fill = author)) +
  geom_col(show.legend = FALSE) +
  labs(x = NULL, y = "tf-idf") +
  facet_wrap(~author, scales = "free") +
  coord_flip() +
  theme_minimal() +
  scale_fill_viridis_d() +
  labs(title = "Most distinctive words in each manifesto")

Selecting by tf_idf

And here is the graph showing the tf-idfs.