Text Mining Lab
Julia Burek
10/20/2021
library(tidyverse)
library(tidytext)
library(ggwordcloud)
library(gutenbergr)
library(textdata)1 Reading in Text for Different Regions
# Read in Text for Articles from Southern Region (Julia)
south <- read_lines("~/Desktop/DS3001/DS 3001/07_text_mining/southern_region")
south <- tibble(south)
south$south <- as.character(south$south)
south <- south %>%
unnest_tokens(word, south)%>%
anti_join(stop_words)%>%
count(word, sort=TRUE)
# Read in Text for Articles from Western Region (Jess)
west <- read_lines("~/Desktop/DS3001/DS 3001/07_text_mining/west_coast.txt")
west <- tibble(west)
west$west <- as.character(west$west)
west <- west %>%
unnest_tokens(word, west)%>%
anti_join(stop_words)%>%
count(word, sort=TRUE)
# Read in Text for Articles from Midwestern Region (Kara)
midwest <- read_lines("~/Desktop/DS3001/DS 3001/07_text_mining/midwest_region")
midwest <- tibble(midwest)
midwest$midwest <- as.character(midwest$midwest)
midwest <- midwest %>%
unnest_tokens(word, midwest)%>%
anti_join(stop_words)%>%
count(word, sort=TRUE)2 Sentiments for Different Regions
# Sentiments for Southern Region Articles
south_sentiment_affin <- south %>%
inner_join(get_sentiments("afinn"))
View(south_sentiment_affin)
south_sentiment_nrc <- south %>%
inner_join(get_sentiments("nrc"))
View(south_sentiment_nrc)
south_sentiment_bing <- south %>%
inner_join(get_sentiments("bing"))
View(south_sentiment_bing)
# Negative sentiments are 179 and Positive sentiments are 105
# Sentiments for Western Region Articles
west_sentiment_affin <- west %>%
inner_join(get_sentiments("afinn"))
View(west_sentiment_affin)
west_sentiment_nrc <- west %>%
inner_join(get_sentiments("nrc"))
View(west_sentiment_nrc)
west_sentiment_bing <- west %>%
inner_join(get_sentiments("bing"))
View(west_sentiment_bing)
# Negative sentiments are 161 and Positive sentiments are 81
# Sentiments for Midwestern Region Article
midwest_sentiment_affin <- midwest %>%
inner_join(get_sentiments("afinn"))
View(midwest_sentiment_affin)
midwest_sentiment_nrc <- midwest %>%
inner_join(get_sentiments("nrc"))
View(midwest_sentiment_nrc)
midwest_sentiment_bing <- midwest %>%
inner_join(get_sentiments("bing"))
View(midwest_sentiment_bing)
# Negative sentiments are 159 and Positive sentiments are 79
# Comparison of Regions
table(south_sentiment_bing$sentiment)##
## negative positive
## 179 105table(west_sentiment_bing$sentiment)##
## negative positive
## 161 81table(midwest_sentiment_bing$sentiment)##
## negative positive
## 159 79table(south_sentiment_nrc$sentiment)##
## anger anticipation disgust fear joy negative
## 74 94 43 89 62 170
## positive sadness surprise trust
## 231 63 48 137table(west_sentiment_nrc$sentiment)##
## anger anticipation disgust fear joy negative
## 59 69 37 82 44 137
## positive sadness surprise trust
## 187 58 33 116table(midwest_sentiment_nrc$sentiment)##
## anger anticipation disgust fear joy negative
## 68 84 30 88 53 142
## positive sadness surprise trust
## 189 70 41 108Conclusion: For the Southern Region, I saw there were
3 Plot of Sentiments for Different Regions
# Plot of Southern Region's Sentiment Range
ggplot(data = south_sentiment_affin,
aes(x=value)
)+
geom_histogram(bins=20)+
ggtitle("Southern Region Sentiment Range")+
theme_minimal()
# Plot of Western Region's Sentiment Range
ggplot(data = west_sentiment_affin,
aes(x=value)
)+
geom_histogram(bins=20)+
ggtitle("Western Region Sentiment Range")+
theme_minimal()
# Plot of Midwestern Region's Sentiment Range
ggplot(data = midwest_sentiment_affin,
aes(x=value)
)+
geom_histogram(bins=20)+
ggtitle("Midwestern Region Sentiment Range")+
theme_minimal()
4 Word Clouds for Different Regions
# Word Cloud for Southern Region
set.seed(42)
ggplot(south[1:50,], aes(label = word, size = n)
) +
geom_text_wordcloud() +
theme_minimal()
# Word Cloud for Western Region
set.seed(42)
ggplot(west[1:50,], aes(label = word, size = n)
) +
geom_text_wordcloud() +
theme_minimal()
# Word Cloud for Midwestern Region
set.seed(42)
ggplot(midwest[1:50,], aes(label = word, size = n)
) +
geom_text_wordcloud() +
theme_minimal()
Conclusion: For the Southern Region, words like “climate”, “change”, “global”, “warming”, “energy”, “republicans”, “conservatives”, and “carbon”, were among some of the more common occurring words in the articles from this region. For word sentiments for the Southern Region, there were 179 negative sentiments and 105 positive sentiments. This shows that there is a bit more negative language regarding climate change. The positive sentiment number was a bit higher than I expected, however. The reason the positive sentiment could be a bit higher may be due to the fact that some individuals in the Southern region do not see climate change as an important of an issue compared to other regions. The Southern region has several Red states and despite changing beliefs over the years, Republicans have historically denied the gravity of climate change. This is why I think there is not as much of a difference between negative and positive sentiment compared to that of the Western region, for example. For many Republicans, climate change is viewed as a political issue. For this reason, I was not surprised to see the words “republicans” and “conservatives” in larger text on the word cloud. Many Republican politicians, such as President Donald Trump, have used concerning language about climate change, denying or downplaying the gravity of climate change. Some of these politicians have even blocked or rolled back policies to combat climate change. For the Southern region, which has a large Republican population, many individuals continue to see climate change as a political issue which is supported by the text mining I performed for this region.
5 Term Frequency - Inverse Document Frequency for Regions
# Term Frequency - Inverse Document Frequency (tf-idf)
south_raw <- as.tibble(read_lines("~/Desktop/DS3001/DS 3001/07_text_mining/southern_region"))
west_raw <- as.tibble(read_lines("~/Desktop/DS3001/DS 3001/07_text_mining/west_coast.txt"))
midwest_raw <- as.tibble(read_lines("~/Desktop/DS3001/DS 3001/07_text_mining/midwest_region"))
data_prep <- function(x,y,z){
i <- as_tibble(t(x))
ii <- unite(i,"text",y:z,remove = TRUE,sep = "")
}
south_bag <- data_prep(south_raw[1:371,1],'V1','V371')
west_bag <- data_prep(west_raw,'V1','V141')
midwest_bag <- data_prep(midwest_raw,'V1','V204')
region <- c("South","West","Midwest")
tf_idf_text <- tibble(region,text=t(tibble(south_bag,west_bag,midwest_bag,.name_repair = "universal")))
View(tf_idf_text)
word_count <- tf_idf_text %>%
unnest_tokens(word, text) %>%
count(region, word, sort = TRUE)
total_words <- word_count %>%
group_by(region) %>%
summarize(total = sum(n))
region_words <- left_join(word_count, total_words)
region_words <- region_words %>%
bind_tf_idf(word, region, n)
region_words## # A tibble: 7,288 × 7
## region word n total tf idf tf_idf
## <chr> <chr> <int> <int> <dbl> <dbl> <dbl>
## 1 South the 498 8857 0.0562 0 0
## 2 West the 467 8091 0.0577 0 0
## 3 Midwest the 421 7749 0.0543 0 0
## 4 South to 258 8857 0.0291 0 0
## 5 Midwest to 251 7749 0.0324 0 0
## 6 South of 247 8857 0.0279 0 0
## 7 West of 236 8091 0.0292 0 0
## 8 West and 228 8091 0.0282 0 0
## 9 South and 220 8857 0.0248 0 0
## 10 West to 218 8091 0.0269 0 0
## # … with 7,278 more rowstop10 <- region_words%>%
arrange(desc(tf_idf))%>%
group_by(region)%>%
slice(1:10)
fig <- ggplot(top10, aes(tf_idf, word, fill = tf_idf)) +
geom_col(show.legend = FALSE) +
facet_wrap(~region, scales = "free_y") +
labs(x = "Regions and Most Impactful Words",
y = NULL)
fig