Some changes made to data cleaning process.

# New dataframe for data cleaning

reviews.clean <- gamereviews

#clean.review <- function(review) {

#  cleaned.review <- gsub("[^[:print:]]", "", review) # remove non-ASCII character

#  cleaned.review <- gsub("(?<=\\w)n't", " not", review, perl = TRUE) # replacing n't with not with an empty space

#  cleaned.review <- gsub("http[s]?://\\S+", " ", cleaned.review) # Remove URLs

#  cleaned.review <- gsub("(.)\\1{2,}", "\\1 ", cleaned.review) # Replace consecutive repeated characters with a single character

#  cleaned.review <- gsub("\\d", " ", cleaned.review) # Remove digits

#  cleaned.review <- gsub("[[:punct:]]", " ", cleaned.review) # Remove punctuation

#  cleaned.review <- gsub("\\n", " ", cleaned.review) # Replace newline characters with a space

#  cleaned.review <- gsub("\\s+", " ", cleaned.review) # Replace multiple spaces with a single space

#  cleaned.review <- ifelse(nchar(cleaned.review) == 1, " ", cleaned.review) # Remove single-character reviews

#  cleaned.review <- gsub("^\\s+|\\s+$", "", cleaned.review) # Remove leading and trailing whitespaces

  # Remove stopwords (except "not") using tm package

#  stop_words <- stopwords("english")

#  stop_words <- setdiff(stop_words, "not")

#  

#  cleaned.review <- paste(

#    unlist(

#      lapply(strsplit(cleaned.review, " "), 

#             function(word) ifelse(tolower(word) %in% stop_words, "", word)

#      )

#    ), 

#    collapse = " "

#  )

#  

#  return(cleaned.review)

#}

reviews.clean$reviews <- gsub("[^\\x00-\\x7F]+", "", reviews.clean$review, perl = TRUE) # remove non-ASCII character

print(reviews.clean$reviews[4546])

# Setting a working directory to save dataset

setwd("D:/Hohenheim/SEM 3/ADS/introads_ass2_team18/01_data")

# Save the final dataframe after all cleaning tasks

write.csv(reviews.clean, file = "reviews.clean.csv")

save(reviews.clean, file = "reviews.clean.RData")

# word cloud--------------------------------------------------------------------