Understanding End-user Needs from #VisionZero

setwd("C:/Users/s-das/Syncplicity Folders/MyProjects_IMP/Data_TTI_Works/TwitterData/PrevData/VisionZero_and_SelfDriving_and_Transit/Twitter_Final/Original")
dat <- read.csv("VisionZero_all_07162019_v2.csv")
dim(dat)

## [1] 32001     5

library(tidytext)
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

dat$text <- as.character(dat$text)

dat2= dat %>%
  unnest_tokens(word, text) %>% 
  mutate(lines = rownames(.)) %>% 
  filter(grepl("need|want|wish|feature|ask|improve|idea|upgrade|
support|problem|issue|help|fix|complain|fail|solve|countermeasure|treatment|require|demand|urgent|urgency|
please", word)) 
dat3 <- left_join(dat2[,c(1, 3, 4, 5)], dat[,c(1, 2)], by="ID")
dat3 <- dat3[,c(2,5,4,3)]
dim(dat3)

## [1] 4089    4

dim(dat2)

## [1] 4089    6

dim(dat)

## [1] 32001     5

library(DT)
datatable(dat3)

## Warning in instance$preRenderHook(instance): It seems your data is too
## big for client-side DataTables. You may consider server-side processing:
## https://rstudio.github.io/DT/server.html