Load data
library(tidyverse)
keywords <- read_tsv("weighted_keywords_clean.tsv")
keywords_academic <- read_tsv("weighted_keywords_academic_clean.tsv")
head(keywords, n = 200)
## # A tibble: 200 × 7
## Term Focus rel. freq. (S…¹ Refer…² Simpl…³ Log l…⁴ % dif…⁵ Log r…⁶
## <chr> <dbl> <dbl> <dbl> <dbl> <chr> <dbl>
## 1 salience 15914. 2.61 156. 8647. 610,30… 12.6
## 2 linguistic 4108. 10.8 38.0 13854. 38,111… 8.58
## 3 salient 3210. 3.71 31.9 3863. 86,422… 9.76
## 4 attention 4971. 119. 23.1 159395. 4,071.… 5.38
## 5 language 4280. 110. 20.9 193479. 3,799.… 5.29
## 6 lexical 2037. 5.32 20.3 4477 38,172… 8.58
## 7 cognitive 2623. 35.1 20.2 653. 7,373.… 6.22
## 8 bottom-up 1899. 1.9 19.6 732. 99,614… 9.96
## 9 onomasiological 1795. 0 19.0 850. Infini… 47.4
## 10 e.g 1795. 0.5 18.9 879. 360,36… 11.8
## # … with 190 more rows, and abbreviated variable names
## # ¹`Focus rel. freq. (Salience clean: whole corpus)`,
## # ²`Reference rel. freq. (BNC2014: whole corpus)`, ³`Simple maths`,
## # ⁴`Log likelihood`, ⁵`% difference`, ⁶`Log ratio`
head(keywords_academic, n = 200)
## # A tibble: 200 × 7
## Term Focus rel. freq. (S…¹ Refer…² Simpl…³ Log l…⁴ % dif…⁵ Log r…⁶
## <chr> <dbl> <dbl> <dbl> <dbl> <chr> <dbl>
## 1 salience 15914. 13.3 141. 6294. 119,73… 10.2
## 2 salient 3210. 16.3 28.5 935. 19,570… 7.62
## 3 linguistic 4108. 48.2 28.4 1030. 8,422.… 6.41
## 4 onomasiological 1795. 0 19.0 679. Infini… 47.4
## 5 e.g 1795. 0.96 18.8 596. 186,29… 10.9
## 6 bottom-up 1899. 7.45 18.6 575. 25,381… 7.99
## 7 linguistics 1795. 5.58 18.0 560. 32,095… 8.33
## 8 lexical 2037. 27.1 16.8 497. 7,410.… 6.23
## 9 attention 4971. 228. 15.5 38289. 2,080.… 4.45
## 10 top-down 1553. 12.0 14.8 1041. 12,831… 7.01
## # … with 190 more rows, and abbreviated variable names
## # ¹`Focus rel. freq. (Salience clean: whole corpus)`,
## # ²`Reference rel. freq. (BNC2014: academic prose)`, ³`Simple maths`,
## # ⁴`Log likelihood`, ⁵`% difference`, ⁶`Log ratio`
Produce a wordcloud
library(RColorBrewer)
library(wordcloud2)
# Whole BNC2014 Corpus:
keyword_list <- keywords %>% select(Term,`Simple maths`)
wordcloud2(data = keyword_list, color = brewer.pal(8, "Dark2"), gridSize = 10, minSize = 6, size = 2)