Processing

PURPOSE

In this step, the Attenuator tagged words were reinserted into the review text.

PREPARATION

1. Preparation

library(readxl)
library(NLP)
library(tm)

## Warning: package 'tm' was built under R version 3.4.3

library(stringr)
library(ngram)

## Warning: package 'ngram' was built under R version 3.4.3

setwd("~/Google Drive/UM/Smart Services/Thesis/Thesis/Code/Feature Set4/Code/2.Attenuator/4. Processing")

REINSERT TEXT INTO REVIEW

2. Load Data (Tagged Fragments)

#Attenuator Tagging
AttenuatorTagged <- read_excel("~/Google Drive/UM/Smart Services/Thesis/Thesis/Code/Feature Set4/Input/8.AttenuatorTagged.xlsx")

AttenuatorTagged <- AttenuatorTagged$Text
AttenuatorTagged <- as.list(AttenuatorTagged)

3. Load Data (IDs)

Using the Review and Sentence ID, the negated sentences will be reinserted into the review text.

Indeces <- read_excel("~/Google Drive/UM/Smart Services/Thesis/Thesis/Code/Feature Set4/Input/6. Attenuator Sentence Indicators.xlsx")

Final.Sentence.ID <- as.list(Indeces$Attenuator.Index.List)

4. Load Data (Destination Text)

#DESTINATION TEXT
Destination.Text <- read_excel("~/Google Drive/UM/Smart Services/Thesis/Thesis/Code/Feature Set4/Input/5.Reviews with Booster Tagging.xlsx")

Destination.Text <- Destination.Text$BoosterTaggedReviews

5. Reinsert Negative Sentences into Review

Destination.Control <- Destination.Text

for (n in 1:623){
  ID <- Final.Sentence.ID[[n]]
  Text <- AttenuatorTagged[[n]]
  Destination.Text[[ID]] <- Text
}

Destination.Text <- as.list(Destination.Text)

print('Old')

## [1] "Old"

Destination.Control [[36]]

## [1] "On a day with heavy rainfall a pretty common occurrence in ."

print('New')

## [1] "New"

Destination.Text [[36]]

## [1] "On a day with heavy rainfall a common_LOW occurrence in ."

df <- data.frame(matrix(data = seq(1,4735),nrow = 4735,ncol = 1))
df$AttenuatorTaggedReviews <- Destination.Text

WriteXLS::WriteXLS(df,ExcelFileName = "9.Reviews with Booster and Attenuator Tagging.xlsx")