| # Tokenize words | |
| tkn <- tokens(allTweets$text, | |
| remove_twitter = T, | |
| remove_separators = T, | |
| remove_symbols = T, | |
| remove_punct = T, | |
| remove_url = T, | |
| remove_hyphens = T, | |
| remove_numbers = T) %>% | |
| tokens_ngrams(n = 1:2) | |
| gotDfm <- dfm(tkn, tolower = T, | |
| remove = stopwords("english")) | |
| gotChars <- c("jon", "cersei", "sansa", "arya", | |
| "bran", "tyrion", "jaime", "daenerys", | |
| "hound", "davos", "missandei", "theon", | |
| "brienne", "gendry", "grey_worm", "jorah", | |
| "night_king", "varys", "melisandre", "tormund") | |
| gotFcm <- dfm_select(gotDfm, pattern = gotChars) %>% | |
| fcm() | |
| set.seed(100) | |
| textplot_network(gotFcm, min_freq = 0.1, | |
| edge_alpha = .25, | |
| edge_size = 5) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment