Ananlyis on Q1 has been done.

install.packages("RColorBrewer")

install.packages("ggplot2")

install.packages("dyplr")

install.packages("irr")

install.packages("lpSolve")

# Loading of packages

library(tidytext)

library(stringr)

library(syuzhet)

library(NLP)

library(RColorBrewer)

library(ggplot2)

library(dplyr)

library(irr)

library(lpSolve)

#loading necessary dataset

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")

load("C:/Users/akluj/SEM_3/ADS/introads_ass2_team18/01_data/reviews.clean.RData")

load("C:/Users/akluj/SEM_3/ADS/introads_ass2_team18/01_data/raw/gamereviews.RData")

# Only keeping necessary columns for analysis

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

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

# Loading of necessary words lists taken from Kaggel by Hu and Bing Liu

setwd("D:/Hohenheim/SEM 3/ADS/introads_ass2_team18/00_docs")

setwd("C:/Users/akluj/SEM_3/ADS/introads_ass2_team18/00_docs")

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

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

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

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

sent.analysis <- function(review) {

  # Tokenize the review into words

# Display the result

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

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

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

# sentiment score using AFINN dictionary

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

    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", 

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

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

# Calculating weightage of enotions

# Calculating weightage of emotions

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")

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

# Q1 Checking the consistency of sentiment with positive and negative voted_up------------------------------------------------

merged <- merge(rev.sentiment, gamereviews, by.x = "id", by.y = "recommendationid", all.x = TRUE)

# Checking the consistency of sentiment with positive and negative voted_up

merged <- merge(sent.label= rev.sentiment$sent.label, voted_up= gamereviews$voted_up, by.x = "id", 

                by.y = "recommendationid", all.x = TRUE)

comparison <- data.frame(id = merged$id, reviews = merged$reviews, sent.label=merged$sent.label, voted_up=merged$voted_up)

comparison <- comparison %>%

    voted_up==TRUE ~ "Positive",

    voted_up==FALSE ~ "Negative"))

comparison$compare <- ifelse(comparison$sent.label == "Positive" & comparison$voted_up_mapped == "Positive", "positive",

                             ifelse(comparison$sent.label == "Negative" & comparison$voted_up_mapped == "Negative", "positive",

                                    "Neutral"))

# Counting the number of match 

match.count <- sum(comparison$compare=="Match")

mismatch.count <- sum(comparison$compare=="Mismatch")

# Converting 'voted_up' to a factor for better comparison

comparison$voted_up <- as.factor(comparison$voted_up)

total.count <- length(comparison$compare)

# Creating a matrix

conf_matrix <- table(comparison$sent.label, comparison$voted_up)

print(conf_matrix)

# Calculate percentage agreement

total_obs <- sum(conf_matrix)

correct_agreement <- sum(diag(conf_matrix))

percentage_agreement <- correct_agreement / total_obs * 100

# Printing result

cat("Percentage Agreement:", percentage_agreement, "%\n")

# Q2

# Calculating ration of match and mismatch

match.ratio <- match.count / total.count

# Display the result

print(comparison_result)