pushing everything i had in case missed something

DataAnalysis/Q3/BigramWordCloud.R

@@ -18,6 +18,7 @@ foxtitle <- read.csv("/Volumes/GoogleDrive/My Drive/Spring 2022/Data Science Met
 nytitle <- read.csv("/Volumes/GoogleDrive/My Drive/Spring 2022/Data Science Methodology/UkraineConflictOnTwitter/SentimentAnalysis/data/q3/NYT_Sheikh_with_sentiment.csv")
 
 bigram_wc <- function(foxnews){
+  foxnews$text <- removeNumbers(foxnews$text)
   fox_unn <- foxnews %>% unnest_tokens(word, text, token = "ngrams",
                                        n=2) %>% 
     anti_join(stop_words)
@@ -44,12 +45,12 @@ bigram_wc <- function(foxnews){
   return(wc)
 }
 
-fox_pos <- foxnews %>% filter(label=="Positive")
-fox_neg <- foxnews %>% filter(label=="Negative")
-fox_neu <- foxnews %>% filter(label=="Neutral")
+fox_pos <- bigram_wc(foxnews %>% filter(label=="Positive"))
+fox_neg <- bigram_wc(foxnews %>% filter(label=="Negative"))
+fox_neu <- bigram_wc(foxnews %>% filter(label=="Neutral"))
 
-nyt_pos <- nytimes %>% filter(label=="Positive")
-nyt_neg <- nytimes %>% filter(label=="Negative")
-nyt_neu <- nytimes %>% filter(label=="Neutral")
+nyt_pos <- bigram_wc(nytimes %>% filter(label=="Positive"))
+nyt_neg <- bigram_wc(nytimes %>% filter(label=="Negative"))
+nyt_neu <- bigram_wc(nytimes %>% filter(label=="Neutral"))
 
 

DataAnalysis/Q3/MakeWordCloud.R

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

DataAnalysis/Q3/Q3LinePlot.R

@@ -3,11 +3,14 @@ library(dplyr)
 
 # csv file -- change the file path here
 #q1 <-  read.csv('/Volumes/GoogleDrive/My Drive/Spring 2022/Data Science Methodology/UkraineConflictOnTwitter/SentimentAnalysis/data/q1/all_tweets_emotions_with_sentiment.csv')
-#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")
+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")
-q1 <- foxtitle
+q1 <- nytimes
+
+#filter tweets that starts with @
+q1 <- q1 %>%  filter(!grepl("^@", q1$text))
 
 
 ## stacked bar plot ##
@@ -43,7 +46,7 @@ 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("Fox News Average Sentiment of Tweets by Week") +
+  ggtitle("NYTimes 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 +55,6 @@ 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(1,12,19,23), labels=c("Dec 1st", "Feb 24th", "April 12th", "April 30th"))
+  scale_x_continuous(breaks=c(1,11,16,23), labels=c("Dec 24th", "Feb 24th", "April 7th", "May 24th"))
 #scale_color_manual('label', values=c('#d9534f', '#f0ad4e', '#5cb85c', '#5cb86c', '#5cb87c', '#5cb88c', '#5cb89c'))
 

DataAnalysis/Q3/trigramWordCloud.R

@@ -46,11 +46,11 @@ trigram_wc <- function(foxnews){
   return(wc)
 }
 
-fox_pos <- foxnews %>% filter(label=="Positive")
-fox_neg <- foxnews %>% filter(label=="Negative")
-fox_neu <- foxnews %>% filter(label=="Neutral")
+fox_pos <- trigram_wc(foxnews %>% filter(label=="Positive"))
+fox_neg <- trigram_wc(foxnews %>% filter(label=="Negative"))
+fox_neu <- trigram_wc(foxnews %>% filter(label=="Neutral"))
 
-nyt_pos <- nytimes %>% filter(label=="Positive")
-nyt_neg <- nytimes %>% filter(label=="Negative")
-nyt_neu <- nytimes %>% filter(label=="Neutral")
+nyt_pos <- trigram_wc(nytimes %>% filter(label=="Positive"))
+nyt_neg <- trigram_wc(nytimes %>% filter(label=="Negative"))
+nyt_neu <- trigram_wc(nytimes %>% filter(label=="Neutral"))