Quanteda changing rel freq of a term over time - r

Question

I have a corpus of news articles with date and time of publication as 'docvars'.
readtext object consisting of 6 documents and 8 docvars.
# Description: df[,10] [6 × 10]
doc_id text year month day hour minute second title source
* <chr> <chr> <int> <int> <int> <int> <int> <int> <chr> <chr>
1 2014_01_01_10_51_00… "\"新华网伦敦1… 2014 1 1 10 51 0 docid报告称若不减… RMWenv
2 2014_01_01_11_06_00… "\"新华网北京1… 2014 1 1 11 6 0 docid盘点2013… RMWenv
3 2014_01_02_08_08_00… "\"原标题：报告… 2014 1 2 8 8 0 docid报告称若不减… RMWenv
4 2014_01_03_08_42_00… "\"地球可能毁灭… 2014 1 3 8 42 0 docid地球可能毁灭… RMWenv
5 2014_01_03_08_44_00… "\"北美鼠兔看起… 2014 1 3 8 44 0 docid北美鼠兔为应… RMWenv
6 2014_01_06_10_30_00… "\"欣克力C点核… 2014 1 6 10 30 0 docid英国欲建50… RMWenv
I would like to measure the changing relative frequency that a particular term - e.g 'development' - occurs in these articles (either as a proportion of the total terms in the article / or as a proportion of the total terms in all the articles published in a particular day / month). I know that I can count the number of times the term occurs in all the articles in a month, using:
dfm(corp, select = "term", groups = "month")
and that I can get the relative frequency of the word to the total words in the document using:
dfm_weight(dfm, scheme = "prop")
But how do I combine these together to get the frequency of a specific term relative to the total number of words on a particular day or in a particular month?
What I would like to be able to do is measure the change in the amount of times a term is used over time, but accounting for the fact that the total number of words used is also changing. Thanks for any help!

Answer 1

#DaveArmstrong gives a good answer here and I upvoted it, but can add a bit of efficiency using some of the newest quanteda syntax, which is a bit simpler.
The key here is preserving the date format created by zoo::yearmon(), since the dfm grouping coerce that to a character. So we pack it into a docvar, which is preserved by the grouping, and then retrieve it in the ggplot() call.
load(file("https://www.dropbox.com/s/kl2cnd63s32wsxs/music.rda?raw=1"))
library("quanteda")
## Package version: 2.1.1
## create corpus and dfm
corp <- corpus(m, text_field = "body_text")
corp$date <- m$first_publication_date %>%
zoo::as.yearmon()
D <- dfm(corp, remove = stopwords("english")) %>%
dfm_group(groups = "date") %>%
dfm_weight(scheme = "prop")
library("ggplot2")
convert(D[, "wonderfully"], to = "data.frame") %>%
ggplot(aes(x = D$date, y = wonderfully, group = 1)) +
geom_line() +
labs(x = "Date", y = "Wonderfully/Total # Words")

Answer 2

I suspect someone will come up with a better solution within quanteda, but in the event they don't, you could always extract the word from the dfm and put it in a dataset along with the date and then make the graph. In the code below, I'm using some music reviews I scraped from the Guardian's website. I've commented out the functions that read in the data from an .rda file from Dropbox. You're welcomed to use it if you like - it's clean, but I don't want to inadvertently have someone download a file from the web they're not aware of.
# f <- file("https://www.dropbox.com/s/kl2cnd63s32wsxs/music.rda?raw=1")
# load(f)
## create corpus and dfm
corp <- corpus(as.character(m$body_text))
docvars(corp, "date") <- m$first_publication_date
D <- dfm(corp, remove=stopwords("english"))
## take word frequencies "wonderfully" in the dfm
## along with the date
tmp <- tibble(
word = as.matrix(D)[,"wonderfully"],
date = docvars(corp)$date,
## calculate the total number of words in each document
total = rowSums(D)
)
tmp <- tmp %>%
## turn date into year-month
mutate(yearmon =zoo::as.yearmon(date)) %>%
## group by year-month
group_by(yearmon) %>%
## calculate the sum of the instances of "wonderfully"
## divided by the sum of the total words across all
## documents in the month
summarise(prop = sum(word)/sum(total))
## make a plot.
ggplot(tmp, aes(x=yearmon, y=prop)) +
geom_line() +
labs(x= "Date", y="Wonderfully/Total # Words")