you redacted your last post, but I was able to see enough of it to recover something I could make a reprex out of, it does give a result for Topic 5.
first_column <- c("2022-05-31T22:03:15.000Z", "2022-05-31T21:18:46.000Z",
"2022-05-31T20:57:38.000Z", "2022-05-31T18:39:54.000Z", "2022-05-31T18:21:03.000Z")
second_column <- c("1.53176E+18", "1.53175E+18", "1.53174E+18",
"1.53171E+18", "1.5317E+18")
third_column <- c("While neighbourhoods in Oxford are made of dead end streetsJust look at a map of BBLIts a massive LTNBins get collected no issue",
"People making short journeys by car are exactly why LTNs are needed in all residential areas",
"This evening I attended the Fox Lane Residents meeting with ward colleagues Many residents voiced their anger over the LTNs and its ramifications in the local communityMore pollutionmore traffic and more misery 12",
"On the pavementon double yellow lines over a cycle LaneFull house for thisHGV",
"Lime tree flowers in bud todayalongside footcycle path at Via Ravenna mid1980sbuilt highwayLooking forward to our ChiTrees project to understand better how we benefit from these highway trees")
df <- data.frame(first_column, second_column, text=third_column)
library(stm)
library(quanteda)
library(tm)
library(tidyverse)
processed <- textProcessor(df$text, metadata = df)
out <- prepDocuments(processed$documents, processed$vocab, processed$meta)
docs <- out$documents
vocab <- out$vocab
meta <- out$meta
tokens <- df$text %>% tokens(what = "word", remove_punct = TRUE,
remove_numbers = TRUE, remove_url = TRUE) %>% tokens_tolower() %>%
tokens_remove(stopwords("english"))
dfm <- dfm_trim(dfm(tokens), min_docfreq = 0.001, max_docfreq = 0.99,
docfreq_type = "prop", verbose = TRUE)
ldacorpus <- Corpus(VectorSource(tokens))
dfm_stm <- convert(dfm, to = "stm")
model <- stm(documents = dfm_stm$documents, vocab = dfm_stm$vocab,
data = meta, K = 8, verbose = TRUE)
Topic5 <- findThoughts(model,df$text, topics = 5, n = 5)
Topic5