RWIS

1 Titles and Abstracts

1.1 Titles

library(readxl)
library(DT)
library(dplyr)

setwd("C:/Users/s-das/Syncplicity Folders/MyProjects_IMP/MY_Papers_V2/TRB 2021/00_Topics/XML")

tip03 <- read_excel("RWIS.xlsx", sheet="fin")
dim(tip03)

## [1] 75  4

mm=as.data.frame(table(tip03$year))
datatable(mm)

mm=as.data.frame(table(tip03$serial))
datatable(mm)

datatable(tip03)

library(tm)

## Loading required package: NLP

library(tidytext)
library(stopwords)

## 
## Attaching package: 'stopwords'

## The following object is masked from 'package:tm':
## 
##     stopwords

stopwords_regex = paste(stopwords('en'), collapse = '\\b|\\b')
stopwords_regex = paste0('\\b', stopwords_regex, '\\b')
tip03$title1 = stringr::str_replace_all(tip03$title, stopwords_regex, '')


bigram <- tip03 %>%
  unnest_tokens(bigram, title1, token = "ngrams", n = 2) %>%
  count(bigram, sort = TRUE)
datatable(bigram)

trigram <- tip03 %>%
  unnest_tokens(trigram, title1, token = "ngrams", n = 4) %>%
  count(trigram, sort = TRUE)
datatable(trigram)

tetragram <- tip03 %>%
  unnest_tokens(tetragram, title1, token = "ngrams", n = 5) %>%
  count(tetragram, sort = TRUE)
datatable(tetragram)

1.2 Abstracts

stopwords_regex = paste(stopwords('en'), collapse = '\\b|\\b')
stopwords_regex = paste0('\\b', stopwords_regex, '\\b')
tip03$abstract1 = stringr::str_replace_all(tip03$abstract, stopwords_regex, '')

bigram <- tip03 %>%
  unnest_tokens(bigram, title1, token = "ngrams", n = 2) %>%
  count(bigram, sort = TRUE)
datatable(bigram)

trigram <- tip03 %>%
  unnest_tokens(trigram, abstract1, token = "ngrams", n = 3) %>%
  count(trigram, sort = TRUE)
datatable(trigram)

tetragram<- tip03 %>%
  unnest_tokens(trigram, abstract1, token = "ngrams", n = 4) %>%
  count(trigram, sort = TRUE)
datatable(tetragram)