1a) Table showing the total number of words, number of distinct words, and the density for each murder manifesto author.
murder_words |>mutate(word_length =nchar(word)) |>ggplot(aes(word_length)) +facet_wrap(vars(author), scales ="free_y") +geom_histogram(binwidth =1) +labs(title ="Word length distribution for each murder manifesto")
1b) Graph showing the word length distributions for each author.
murder_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) +coord_flip() +facet_wrap(~author, scales ="free") +# creates separate graphs for each authorscale_fill_viridis_d() +# uses a nicer color schemetheme_minimal() +# removes the gray backgroundlabs(x =NULL, y ="Most common words")
Selecting by n
2a) Graph showing the most common words used by each author.
murder_words |>anti_join(snowball) |>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) +coord_flip() +facet_wrap(~author, scales ="free") +# creates separate graphs for each authorscale_fill_viridis_d() +# uses a nicer color schemetheme_minimal() +# removes the gray backgroundlabs(x =NULL, y ="Most common words")
Joining with `by = join_by(word)`
Selecting by n
2b) Graphs showing the most common words (with filler/stop words removed) for each author.
murder_word_counts <- manifestoes |># This counts each word per authorunnest_tokens(word, text) |>count(author, word, sort =TRUE) total_words <- murder_word_counts |># This counts total words per authorgroup_by(author) |>summarize(total =sum(n))murder_word_counts <-left_join(murder_word_counts, total_words) # Joins the two
# A tibble: 5,879 × 7
author word n total tf idf tf_idf
<chr> <chr> <int> <int> <dbl> <dbl> <dbl>
1 Cho you 130 1971 0.0660 0.405 0.0267
2 Cho your 34 1971 0.0173 1.10 0.0190
3 Cho fuck 19 1971 0.00964 1.79 0.0173
4 Breivik cultural 42 5186 0.00810 1.79 0.0145
5 Breivik marxism 37 5186 0.00713 1.79 0.0128
6 Auvinen intelligent 10 1750 0.00571 1.79 0.0102
7 Auvinen minded 10 1750 0.00571 1.79 0.0102
8 Cho jesus 18 1971 0.00913 1.10 0.0100
9 Unabomber leftist 27 5100 0.00529 1.79 0.00949
10 Breivik frankfurt 27 5186 0.00521 1.79 0.00933
# ℹ 5,869 more rows
3a) Table showing the Term-Frequency - Inverse Document Frequency (TF - IDF) for each author. Basically showing which words were unique to each murder, how unique it was, and how many times the author used the word.
murder_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") +theme_minimal() +scale_fill_viridis_d() +labs(title ="Most distinctive words in each murder manifesto") +coord_flip()
Selecting by tf_idf
3b) Graph showing the Term-Frequency - Inverse Document Frequency (TF - IDF) for each author. Basically showing which words were unique to each murder, how unique it was, and how many times the author used the word.
murder_words |>inner_join(bing) |>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 ="Murder manifestos: Words that contribute the most to each sentiment",x =NULL) +scale_fill_viridis_d() +coord_flip() +theme_minimal()
Joining with `by = join_by(word)`
Selecting by n
4) Sentiment analysis graph of the most common positive and negative words. As you can see, these murderers did not get their mouths washed out with soap enough as kids.
manifestoes |>unnest_tokens(bigram, text, token ="ngrams", n =2) |>select(bigram) -> murder_bigrams
murder_bigrams |>count(bigram, sort = T)
# A tibble: 14,954 × 2
bigram n
<chr> <int>
1 of the 159
2 in the 81
3 to the 69
4 i was 60
5 and the 56
6 to be 43
7 political correctness 37
8 i had 34
9 it is 34
10 it was 30
# ℹ 14,944 more rows
# A tibble: 4,115 × 2
bigram n
<chr> <int>
1 political correctness 37
2 frankfurt school 22
3 jesus christ 17
4 cultural marxism 16
5 black man 12
6 human race 12
7 modern leftism 9
8 power process 9
9 surrogate activities 9
10 will never 9
# ℹ 4,105 more rows
5b) Table showing the most common bigrams with the stop words removed.
first_word <-c("they", "will") # these need to be lowercasemurder_bigrams |>count(bigram, sort = T) |>separate(bigram, c("word1", "word2"), sep =" ") |># separate the two wordsfilter(word1 %in% first_word) |># find first words from our listcount(word1, word2, wt = n, sort =TRUE) |>mutate(word2 =factor(word2, levels =rev(unique(word2)))) |># put the words in ordergroup_by(word1) |>top_n(5) |>ggplot(aes(word2, n, fill = word1)) +scale_fill_viridis_d() +# set the color palettegeom_col(show.legend =FALSE) +labs(x =NULL, y =NULL, title ="Word following:") +facet_wrap(~word1, scales ="free") +coord_flip() +theme_minimal()
Selecting by n
6) The first words I used were “they” and “will”. The graph above shows the most common words that follow “they” and “will”.
