Emotion analysis has been done with plotting.

install.packages("syuzhet")

install.packages("NLP")

install.packages("tm")

install.packages("wordcloud")

install.packages("RColorBrewer")

install.packages("ggplot2")

install.packages("dyplr")

# Loading of packages

library(tidytext)

library(stringr)

library(syuzhet)

library(NLP)

library(tm)

library(wordcloud)

library(RColorBrewer)

library(ggplot2)

library(dplyr)

#loading necessary dataset

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

reviews.clean <- read.csv("reviews.clean.csv")

load("D:/Hohenheim/SEM 3/ADS/introads_ass2_team18/01_data/reviews.clean.RData")

load("D:/Hohenheim/SEM 3/ADS/introads_ass2_team18/01_data/raw/gamereviews.RData")

# Only keeping necessary columns for analysis

rev.sentiment <- data.frame(reviews = reviews.clean$review)

rev.sentiment <- data.frame(reviews = reviews.clean$reviews)

# Manual sentiment analysis-----------------------------------------------------

positive.words <- readLines("positive-words.txt")

negative.words <- readLines("negative-words.txt")

# Function to perform sentiment analysis on a single review; in a code, sent=sentiment

# Function to perform sentiment analysis on a single review.sent=sentiment

sent.analysis <- function(review) {

  # Tokenize the review into words

    sent.score <- sent.score * -1

  }

  # Ascribe positive (1), negative (-1), or neutral (0) sentiment

  # sentiment labeling positive (1), negative (-1), or neutral (0)

  sentiment <- ifelse(sent.score > 0, 1, ifelse(sent.score < 0, -1, 0))

  return(sentiment)

}

# Apply sentiment analysis to all reviews in the dataframe

rev.sentiment$sentiment.score <- sapply(rev.sentiment$reviews, sent.analysis)

rev.sentiment$sent.score <- sapply(rev.sentiment$reviews, sent.analysis)

# Labeling the sentiment score with sentiment

rev.sentiment$sentiment.label <- ifelse(rev.sentiment$sentiment.score == 1, "Positive",

                                        ifelse(rev.sentiment$sentiment.score == -1, "Negative", "Neutral"))

rev.sentiment$sent.label <- ifelse(rev.sentiment$sent.score == 1, "Positive",

                                        ifelse(rev.sentiment$sent.score == -1, "Negative", "Neutral"))

# Counting the total number reviews:

positive.counts <- sum(rev.sentiment$sentiment.label == "Positive")

positive.counts <- sum(rev.sentiment$sent.label == "Positive")

cat("The total number of positive reviews are", positive.counts)

negative.counts <- sum(rev.sentiment$sentiment.label == "Negative")

negative.counts <- sum(rev.sentiment$sent.label == "Negative")

cat("The total number of negative reviews are", negative.counts)

neutral.counts <- sum(rev.sentiment$sentiment.label == "Neutral")

neutral.counts <- sum(rev.sentiment$sent.label == "Neutral")

cat("The total number of neutral reviews are", neutral.counts)

# Syuzhet sentiment analysis using bing dictionary------------------------------

rev.sentiment$score.syuzhet <- get_sentiment(rev.sentiment$reviews, method = "bing")

# Labeling the sentiment score with sentiment

rev.sentiment$sent.label.syuzhet <- ifelse(rev.sentiment$score.syuzhet >= 1, "Positive",

rev.sentiment$label.syuzhet <- ifelse(rev.sentiment$score.syuzhet >= 1, "Positive",

                                        ifelse(rev.sentiment$score.syuzhet <= -1, "Negative", "Neutral"))

# Sentiment scores by manually and with syuzhet package and chceking if its identical or not

rev.sentiment$identical.score <- ifelse(rev.sentiment$sentiment.score == score.syuzhet, 1 , 0)

# Sentiment scores by manually and with syuzhet package and checking if its identical or not

rev.sentiment$identical.score <- ifelse(rev.sentiment$sent.score == rev.sentiment$score.syuzhet, 1 , 0)

# Calculate the percentage of identical scores

percentage.identical <- mean(rev.sentiment$identical.score) * 100

# Display the result

cat("Percentage of Identical Score:", percentage.identical, "%\n")

cat("Percentage of Identical Score:", round(percentage.identical,2), "%\n")

# Sentiment analysis by using other two dictionaries from syuhet package--------

rev.sentiment$score.afinn <- get_sentiment(rev.sentiment$reviews, method = "afinn")

# Labeling sentiment score with sentiment

rev.sentiment$sent.label.afinn <- ifelse(rev.sentiment$score.afinn >= 1, "Positive",

rev.sentiment$label.afinn <- ifelse(rev.sentiment$score.afinn >= 1, "Positive",

                                         ifelse(rev.sentiment$score.afinn <= -1, "Negative", "Neutral"))

# Sentiment score using nrc dictionary

rev.sentiment$score.nrc <- get_nrc_sentiment(rev.sentiment$reviews)

# Wordcloud based on emotions---------------------------------------------------

reviews <- rev.sentiment$reviews

# Emotion analysis---------------------------------------------------

# Extract the NRC emotion scores for each term

# Assuming 'nrc_scores' is a column containing NRC scores for each review in your rev.sentiment dataframe

nrc_scores <- rev.sentiment$score.nrc

# Extracting the NRC emotion scores for each term

nrc.scores <- rev.sentiment$score.nrc

#Sum the NRC scores for each emotion across all reviews

aggregate_nrc <- colSums(nrc_scores, na.rm = TRUE)

nrc.scores <- colSums(nrc.scores, na.rm = TRUE)

# Convert the aggregated scores to a data frame

nrc_aggregated_df <- data.frame(emotion = names(aggregate_nrc), score = aggregate_nrc)

# Remove rows with NAs (if any)

nrc_aggregated_df <- nrc_aggregated_df[complete.cases(nrc_aggregated_df), ]

# Create the word cloud

wordcloud(words = nrc_aggregated_df$emotion, freq = nrc_aggregated_df$score, 

          min.freq = 1, scale = c(3, 0.5), colors = brewer.pal(8, "Dark2"))

nrc.scores <- data.frame(emotion = names(nrc.scores), score = nrc.scores)

# Order the dataframe by scores in descending order

nrc.scores <- nrc.scores[order(-nrc.scores$score), ]

# Define a custom color palette with light colors

custom_palette <- c("#a1d99b", "#f03b20", "#FFC3A0", "#FF677D", "#D4A5A5", "#fec44f", "#e6550d", "#fc9272", "#9ecae1", "#bdbdbd")

# Reorder the factor levels of emotion based on scores

nrc.scores$emotion <- factor(nrc.scores$emotion, levels = nrc.scores$emotion)

# Bar plotting of emotions with values

ggplot(nrc.scores, aes(x = emotion, y = score, fill = emotion)) +

  geom_bar(stat = "identity", color = "black", width = 0.7) +

  geom_text(aes(label = round(score, 2)), vjust = 1.5, color = "black", size = 3) + 

  scale_fill_manual(values = custom_palette) +

  labs(title = "Emotion Scores",

       x = "Emotions",

       y = "Scores") +

  theme(legend.position = "bottom", 

    legend.box.margin = margin(3, 3, 3, 3), 

    plot.title = element_text(hjust = 0.5, face = "bold"),  # Bolds the title text

    axis.title.x = element_text(face = "bold"),  # Bolds the x-axis title text

    axis.title.y = element_text(face = "bold"),  # Bolds the y-axis title text

    axis.text.x = element_text(angle = 45, hjust = 1, size = 8, face = "bold"),  # Bolds the x-axis text

    plot.margin = margin(25, 25, 25, 25),  # right margin for legend

    legend.key.size = unit(0.5, "cm")) # size adjust for legend-key

ggsave(file= "C:/Users/hetvi/OneDrive/Desktop/Emotions.jpg", 

       width=15, height=15, units = "cm", dpi=1600)

# Calculating weightage of enotions

nrc.scores <- nrc.scores %>%

  mutate(weightage = score / sum(score) *100)

cat("An emotion with highest weightage is positive with", round(nrc.scores$weightage[1],2),"%\n")

cat("An emotion with highest weightage is disgust with", round(nrc.scores$weightage[10],2),"%\n")

# Checking the consistency of sentiment with positive and negative voted_up