如何查找和绘制多个短语总计的频率？

问题描述

我有语料库，我试图找到按年份总计的多个短语的频率并绘制它。例如，如果“美国经济”和“加拿大经济”这两个词在 2004 年分别被提及 2 次，我希望在 2004 年的频率为 4。

我已经设法为单个标记做到了这一点，但在尝试短语时遇到了麻烦。 这是我以前为单个令牌所做的代码。

a_corpus <- corpus(df,text = "text")

my_dict <- dictionary(list(america = c("America","President")))
                      
freq_grouped_creators <- textstat_frequency(dfm(tokens(a_corpus)),groups = a_corpus$Year)

freq_word_creators <- subset(freq_grouped_creators,freq_grouped_creators$feature %in% my_dict$america)

# collapsing rows by year to total frequencies for tokens
freq_word_creators_2 <- freq_word_creators %>% 
                           group_by(group) %>%
                           summarize(Sum_frequency = sum(frequency))

# plotting
ggplot(freq_word_creators_2,aes(x = group,y = 
    Sum_frequency)) +
    geom_point() +
    scale_y_continuous(limits = c(0,300),breaks = c(seq(0,300,30))) +
    xlab(NULL) +
    ylab("Frequency") +
    theme(axis.text.x = element_text(angle = 90,hjust = 1))

解决方法

无需在 dplyr 中操作频率 - 更简单的方法是选择短语，然后创建一个 dfm，将其转换为 data.frame 以直接与 ggplot2。

library("quanteda")
## Package version: 3.0.9000
## Unicode version: 13.0
## ICU version: 69.1
## Parallel computing: 12 of 12 threads used.
## See https://quanteda.io for tutorials and examples.
library("quanteda.textstats")

a_corpus <- tail(data_corpus_inaugural,10)

economic_phrases <- c("middle class","social security","strong economy")
toks <- tokens(a_corpus)
toks <- tokens_compound(toks,phrase(economic_phrases),concatenator = " ") %>%
  tokens_keep(economic_phrases)
dfmat <- dfm(toks)
dfmat
## Document-feature matrix of: 10 documents,2 features (65.00% sparse) and 4 docvars.
##               features
## docs           middle class social security
##   1985-Reagan             0               0
##   1989-Bush               0               0
##   1993-Clinton            0               0
##   1997-Clinton            2               0
##   2001-Bush               0               1
##   2005-Bush               0               1
## [ reached max_ndoc ... 4 more documents ]

freq_word_creators_2 <- data.frame(convert(dfmat,to = "data.frame"),Year = dfmat$Year)

# plotting
library("ggplot2")
ggplot(freq_word_creators_2,aes(x = Year,y = middle.class)) +
  geom_point() +
  # scale_y_continuous(limits = c(0,300),breaks = c(seq(0,300,30))) +
  xlab(NULL) +
  ylab("Frequency") +
  theme(axis.text.x = element_text(angle = 90,hjust = 1))