some new graphs and stuff

DataAnalysis/Q3/BigramWordCloud.R

@@ -24,7 +24,7 @@ bigram_wc <- function(foxnews){
   bg_fox <- fox_unn %>% 
     separate(word, c("word1", "word2"), sep=" ")
 
-  avoid_list <- c("russia", "ukraine", "user", "http", "fox", "york")
+  avoid_list <- c("russia", "ukraine", "user", "http", "fox", "york", "tucker")
   filter_bg_fox <- bg_fox %>% 
     filter(!word1 %in% stop_words$word) %>% 
     filter(!word2 %in% stop_words$word) %>% 
@@ -52,4 +52,4 @@ nyt_pos <- nytimes %>% filter(label=="Positive")
 nyt_neg <- nytimes %>% filter(label=="Negative")
 nyt_neu <- nytimes %>% filter(label=="Neutral")
 
-filter_by_date <- 
+

DataAnalysis/Q3/MakeWordCloud.R

@@ -42,5 +42,5 @@ make_cloud <- function(dataset, sentiment){
 
 }
 
-make_cloud(foxnews, "Neutral")
+make_cloud(foxnews, "Negative")
 

DataAnalysis/Q3/Q3LinePlot.R

@@ -43,7 +43,7 @@ ggplot(sentiment_by_week, aes(fill=label, y=freq, x=Week, col=label)) +
   geom_line(lwd=1.5) +
   theme_minimal() + 
   theme(panel.background = element_blank()) +
-  ggtitle("NY Times Average Emotions of Tweets by Week") +
+  ggtitle("Fox News Average Sentiment of Tweets by Week") +
   labs(x='Week', y='Frequency') +
   theme(plot.title = element_text(hjust = 0.5, size=15, face='bold', margin = margin(t = 10, r = 0 , b = 10, l = 0))) +
   theme(axis.title.x = element_text(face='bold', size=10, margin = margin(t = 10, b = 10, r = 0, l = 0))) +
@@ -52,6 +52,6 @@ ggplot(sentiment_by_week, aes(fill=label, y=freq, x=Week, col=label)) +
   theme(axis.text.y = element_text(size=10)) +
   theme(legend.title = element_text(face='bold', size=10)) +
   theme(legend.text = element_text(size=8)) +
-  scale_x_continuous(breaks=c(1,11,16,23), labels=c("Dec 24th", "Feb 24th", "April 7th", "May 24th"))
+  scale_x_continuous(breaks=c(1,12,19,23), labels=c("Dec 1st", "Feb 24th", "April 12th", "April 30th"))
 #scale_color_manual('label', values=c('#d9534f', '#f0ad4e', '#5cb85c', '#5cb86c', '#5cb87c', '#5cb88c', '#5cb89c'))
 

DataAnalysis/Q3/Q3RAnalysisSheikh.R

@@ -126,6 +126,9 @@ ggplot(allSent, aes(x=Sentiment, y=Percentage, fill=Source)) +
   geom_bar(stat="identity", width = 1, position = position_dodge()) +
   theme(panel.background = element_blank()) +
   ggtitle("Media Outlet Tweet and Reply Sentiment Comparison") +
+  theme(plot.title = element_text(hjust = 0.5, size=15, face='bold', margin = margin(t = 10, r = 0 , b = 10, l = 0))) +
+  theme(axis.title.x = element_text(face='bold', size=12, margin = margin(t = 10, b = 10, r = 0, l = 0))) +
+  theme(axis.title.y = element_text(face='bold', size=12, margin = margin(t = 0, b = 0, r = 10, l = 10))) +
   scale_fill_manual(values=c("#fc4949", "#1a94eb"))
 
 ###############################################################################

DataAnalysis/Q3/trigramWordCloud.R

@@ -0,0 +1,56 @@
+library(pacman) #my package manager
+
+#load necessary packages
+p_load(ggplot2)
+p_load(dplyr)
+p_load(reshape2)
+p_load(gridExtra)
+p_load(stringr)
+p_load(tidytext)
+p_load(tidyr)
+p_load(wordcloud)
+p_load(tm)
+
+####Loading all the data
+foxnews <- read.csv("/Volumes/GoogleDrive/My Drive/Spring 2022/Data Science Methodology/UkraineConflictOnTwitter/SentimentAnalysis/data/q3/fox_news_Final_with_sentiment.csv")
+nytimes <- read.csv("/Volumes/GoogleDrive/My Drive/Spring 2022/Data Science Methodology/UkraineConflictOnTwitter/SentimentAnalysis/data/q3/new_york_times_Final_with_sentiment.csv")
+foxtitle <- read.csv("/Volumes/GoogleDrive/My Drive/Spring 2022/Data Science Methodology/UkraineConflictOnTwitter/SentimentAnalysis/data/q3/FoxNews_Sheikh_with_sentiment.csv")
+nytitle <- read.csv("/Volumes/GoogleDrive/My Drive/Spring 2022/Data Science Methodology/UkraineConflictOnTwitter/SentimentAnalysis/data/q3/NYT_Sheikh_with_sentiment.csv")
+
+trigram_wc <- function(foxnews){
+  fox_unn <- foxnews %>% unnest_tokens(word, text, token = "ngrams",
+                                       n=3) %>% 
+    anti_join(stop_words)
+  bg_fox <- fox_unn %>% 
+    separate(word, c("word1", "word2", "word3"), sep=" ")
+
+  avoid_list <- c("russia", "ukraine", "user", "http", "fox", "york")
+  filter_bg_fox <- bg_fox %>% 
+    filter(!word1 %in% stop_words$word) %>% 
+    filter(!word2 %in% stop_words$word) %>%
+    filter(!word3 %in% stop_words$word) %>% 
+    filter(!word1 %in% avoid_list) %>% 
+    filter(!word2 %in% avoid_list) %>% 
+    filter(!word3 %in% avoid_list)
+
+  count_bg <- filter_bg_fox %>% 
+    group_by(word1, word2) %>% 
+    tally(sort = TRUE)
+
+  count_bg <- as.data.frame(count_bg)
+
+  count_bg$bigram <- paste(count_bg$word1, count_bg$word2, sep=" ")
+  wc <- wordcloud(words = count_bg$bigram, freq = count_bg$n, min.freq = 1, max.words=200, random.order=FALSE, rot.per=0.35, 
+                  colors=brewer.pal(8, "Dark2"))
+
+  return(wc)
+}
+
+fox_pos <- foxnews %>% filter(label=="Positive")
+fox_neg <- foxnews %>% filter(label=="Negative")
+fox_neu <- foxnews %>% filter(label=="Neutral")
+
+nyt_pos <- nytimes %>% filter(label=="Positive")
+nyt_neg <- nytimes %>% filter(label=="Negative")
+nyt_neu <- nytimes %>% filter(label=="Neutral")
+