R Notebook

require(tidyverse)
require(shiny)

Loading required package: shiny

# Load
require("tm")
require("SnowballC")
require("wordcloud")
require("RColorBrewer")
require("syuzhet")
require("ggplot2")

# Read the text file from local machine , choose file interactively
text <- read_lines("https://raw.githubusercontent.com/adamnorstrom/File/main/WikiData.csv")
# Load the data as a corpus
TextDoc <- Corpus(VectorSource(text))

TextDoc[1]

<<SimpleCorpus>>
Metadata:  corpus specific: 1, document level (indexed): 0
Content:  documents: 1

#Replacing "/", "@" and "|" with space
toSpace <- content_transformer(function (x , pattern ) gsub(pattern, " ", x))
TextDoc <- tm_map(TextDoc, toSpace, "/")

Warning in tm_map.SimpleCorpus(TextDoc, toSpace, "/") :
  transformation drops documents

TextDoc <- tm_map(TextDoc, toSpace, "@")

Warning in tm_map.SimpleCorpus(TextDoc, toSpace, "@") :
  transformation drops documents

TextDoc <- tm_map(TextDoc, toSpace, "\\|")

Warning in tm_map.SimpleCorpus(TextDoc, toSpace, "\\|") :
  transformation drops documents

# Convert the text to lower case
TextDoc <- tm_map(TextDoc, content_transformer(tolower))

Warning in tm_map.SimpleCorpus(TextDoc, content_transformer(tolower)) :
  transformation drops documents

# Remove numbers
TextDoc <- tm_map(TextDoc, removeNumbers)

Warning in tm_map.SimpleCorpus(TextDoc, removeNumbers) :
  transformation drops documents

# Remove english common stopwords
TextDoc <- tm_map(TextDoc, removeWords, stopwords("english"))

Warning in tm_map.SimpleCorpus(TextDoc, removeWords, stopwords("english")) :
  transformation drops documents

# Remove your own stop word
# specify your custom stopwords as a character vector
TextDoc <- tm_map(TextDoc, removeWords, c("s", "company", "team")) 

Warning in tm_map.SimpleCorpus(TextDoc, removeWords, c("s", "company", "team")) :
  transformation drops documents

# Remove punctuations
TextDoc <- tm_map(TextDoc, removePunctuation)

Warning in tm_map.SimpleCorpus(TextDoc, removePunctuation) :
  transformation drops documents

# Eliminate extra white spaces
TextDoc <- tm_map(TextDoc, stripWhitespace)

Warning in tm_map.SimpleCorpus(TextDoc, stripWhitespace) :
  transformation drops documents

# Text stemming - which reduces words to their root form
TextDoc <- tm_map(TextDoc, stemDocument)

Warning in tm_map.SimpleCorpus(TextDoc, stemDocument) :
  transformation drops documents

# Build a term-document matrix
TextDoc_dtm <- TermDocumentMatrix(TextDoc)
dtm_m <- as.matrix(TextDoc_dtm)
# Sort by descending value of frequency
dtm_v <- sort(rowSums(dtm_m),decreasing=TRUE)
dtm_d <- data.frame(word = names(dtm_v),freq=dtm_v)
# Display the top 5 most frequent words
head(dtm_d, 5)

# Plot the most frequent words
plotmain = barplot(dtm_d[1:5,]$freq, las = 2, names.arg = dtm_d[1:5,]$word,
        col ="lightgreen", main ="Top 5 most frequent words",
        ylab = "Word frequencies")

server <- function(input, output) {
  output$plot <- renderPlot(ggplot(dtm_d[1:5,], aes(x = yield)) +  # Create object called `output$plot` with a ggplot inside it
  geom_bar(bins = 5,  # Add a histogram to the plot
    fill = "grey",  # Make the fill colour grey
    data = dtm_d,  # Use data from `Barley`
    colour = "black")  # Outline the bins in black
  )                                                       
}

set.seed(1234)
wordcloud(words = dtm_d$word, freq = dtm_d$freq, min.freq = 5,
          max.words=100, random.order=FALSE, rot.per=0.40, 
          colors=brewer.pal(8, "Dark2"))

# regular sentiment score using get_sentiment() function and method of your choice
# please note that different methods may have different scales
syuzhet_vector <- get_sentiment(text, method="syuzhet")
# see the first row of the vector
head(syuzhet_vector)

[1] 0.00 1.05 1.30 4.55 1.40 3.25

# see summary statistics of the vector
summary(syuzhet_vector)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
 -1.800   1.125   2.850   3.517   5.225  11.050 

# bing
bing_vector <- get_sentiment(text, method="bing")
head(bing_vector)

[1]  0  1  1 -1  2 -1

summary(bing_vector)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
 -4.000   0.000   1.000   2.118   3.000  12.000 

#affin
afinn_vector <- get_sentiment(text, method="afinn")
head(afinn_vector)

[1] 0 3 6 9 5 3

summary(afinn_vector)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
 -5.000   1.000   5.000   6.392   9.000  33.000 

#compare the first row of each vector using sign function
rbind(
  sign(head(syuzhet_vector)),
  sign(head(bing_vector)),
  sign(head(afinn_vector))
)

     [,1] [,2] [,3] [,4] [,5] [,6]
[1,]    0    1    1    1    1    1
[2,]    0    1    1   -1    1   -1
[3,]    0    1    1    1    1    1

# run nrc sentiment analysis to return data frame with each row classified as one of the following
# emotions, rather than a score: 
# anger, anticipation, disgust, fear, joy, sadness, surprise, trust 
# It also counts the number of positive and negative emotions found in each row
d<-get_nrc_sentiment(text)

Warning: `spread_()` was deprecated in tidyr 1.2.0.
Please use `spread()` instead.
This warning is displayed once every 8 hours.
Call `lifecycle::last_lifecycle_warnings()` to see where this warning was generated.

# head(d,10) - to see top 10 lines of the get_nrc_sentiment dataframe

head (d,10)

#transpose
td<-data.frame(t(d))

td

#The function rowSums computes column sums across rows for each level of a grouping variable.
td_new <- data.frame(rowSums(td[10:51]))

#Transformation and cleaning
names(td_new)[1] <- "count"
td_new <- cbind("sentiment" = rownames(td_new), td_new)
rownames(td_new) <- NULL
td_new2<-td_new[1:8,]
#Plot One - count of words associated with each sentiment
quickplot(sentiment, data=td_new2, weight=count, geom="bar", fill=sentiment, ylab="count")+ggtitle("Survey sentiments")

#Plot two - count of words associated with each sentiment, expressed as a percentage
barplot(
  sort(colSums(prop.table(d[, 1:8]))), 
  horiz = TRUE, 
  cex.names = 0.7, 
  las = 1, 
  main = "Emotions in Text", xlab="Percentage"
)