Q2 has been done.

rm(list = ls())

# Installation of packages

install.packages("stringr")

install.packages("syuzhet")

install.packages("NLP")

install.packages("tm")

install.packages("RColorBrewer")

install.packages("ggplot2")

install.packages("dyplr")

install.packages("irr")

install.packages("lpSolve")

install.packages("irr")

# Loading of packages

library(stringr)

library(syuzhet)

library(NLP)

library(tm)

library(RColorBrewer)

library(ggplot2)

library(dplyr)

library(irr)

library(lpSolve)

library(irr)

#loading necessary dataset

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")

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

load("D:/Hohenheim/SEM 3/ADS/introads_ass1_team18-main/01_data/raw/revsummary.RData.csv")

load("D:/Hohenheim/SEM 3/ADS/introads_ass2_team18/01_data/reviews.clean.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("C:/Users/akluj/SEM_3/ADS/introads_ass2_team18/00_docs")

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

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

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

# Sentiment score using nrc dictionary

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

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

# Extracting the NRC emotion scores for each term

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

#Sum the NRC scores for each emotion across all reviews

# Suming up the NRC scores for each emotion across all reviews

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

# Convert the aggregated scores to a data frame

# Converting the aggregated scores to a data frame

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

# Order the dataframe by scores in descending order

# Ordering the dataframe by scores in descending order

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

# Define a custom color palette with light colors

# Defining a custom color palette with light colors using RColorBrewer package

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

# Reorder the factor levels of emotion based on scores

# Reordering 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

# 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)

rev.merged <- merge(rev.sentiment, gamereviews, 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)

# ANother datafarme to particularly check on sentiment consistency

sent.compare <- data.frame(id = rev.merged$id, reviews = rev.merged$reviews, 

                           sent.label=rev.merged$sent.label, voted_up=rev.merged$voted_up)

comparison <- comparison %>%

sent.compare <- sent.compare %>%

  mutate(voted_up_mapped = case_when(

    voted_up==TRUE ~ "Positive",

    voted_up==FALSE ~ "Negative"))

# Converting 'voted_up' to a factor for better comparison

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

sent.compare$voted_up <- as.factor(sent.compare$voted_up)

# Creating a matrix

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

print(conf_matrix)

# Creating a confusion matrix matrix

conf.matrix <- table(sent.compare$sent.label, sent.compare$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

# Calculating a  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")

cat("Percentage Agreement:", percentage.agreement, "%\n")

# Q2 

# Creating a table of counts for each sentiment label

# Adding another column of votes_up to check on the helpfulness of the review

sent.compare$votes_up <- rev.merged$votes_up

sent.count <- table(sent.compare$sent.label)

# Displaying the counts

print(sent.count)

# Calculating an average helpfulness for each sentiment label

avg.sent <- tapply(

  sent.compare$votes_up,

  sent.compare$sent.label,

  mean,

  na.rm = TRUE

)

# Print results

print(avg.sent)

# Finding the index of the review with the highest helpful votes

max.help.index <- which.max(sent.compare$votes_up)

# Getting the corresponding review 

max.helpfulness.review <- sent.compare[max.help.index, ]

# Printing a message for highest helpfulness review

cat("A review with the highest helpfulness is", max.helpfulness.review$sent.label, 

    "sentiment and its' helpfulness rank is", max.helpfulness.review$votes_up, 

    "which is at",max.help.index)

# I crossed check the review in rev.merged dataframe and I found that its sentiment label with 

# all types of sentiment analysis and it's sentiment is being neutral in all. 

# Q3 

 No newline at end of file