exp-9.R

library(tidytext)

## Warning: package 'tidytext' was built under R version 4.3.3

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.4.4     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(textdata)

## Warning: package 'textdata' was built under R version 4.3.3

library(wordcloud2)

## Warning: package 'wordcloud2' was built under R version 4.3.3

library(wordcloud)

## Warning: package 'wordcloud' was built under R version 4.3.3

## Loading required package: RColorBrewer

library(dplyr)

nrc <- get_sentiments("nrc")
load("C:/Users/bmpav/OneDrive/Desktop/geocoded_tweets.rda")
View(geocoded_tweets)
bing <- get_sentiments("bing")
tweet_bing <- geocoded_tweets %>% inner_join(get_sentiments("bing"))

## Joining with `by = join_by(word)`

## Warning in inner_join(., get_sentiments("bing")): Detected an unexpected many-to-many relationship between `x` and `y`.
## ℹ Row 146965 of `x` matches multiple rows in `y`.
## ℹ Row 27 of `y` matches multiple rows in `x`.
## ℹ If a many-to-many relationship is expected, set `relationship =
##   "many-to-many"` to silence this warning.

tweet_nrc <- geocoded_tweets %>% inner_join(get_sentiments("nrc"))

## Joining with `by = join_by(word)`

## Warning in inner_join(., get_sentiments("nrc")): Detected an unexpected many-to-many relationship between `x` and `y`.
## ℹ Row 9 of `x` matches multiple rows in `y`.
## ℹ Row 5 of `y` matches multiple rows in `x`.
## ℹ If a many-to-many relationship is expected, set `relationship =
##   "many-to-many"` to silence this warning.

sad <- tweet_nrc %>% filter(sentiment=='sadness') %>% group_by(word) %>% summarize(freq = mean(freq)) %>% arrange(desc(freq))
View(tweet_nrc)
joy <- tweet_nrc %>% filter(sentiment == "joy") %>% group_by(word) %>% summarize(freq = mean(freq)) %>% arrange(desc(freq))
wordcloud(words = joy$word, freq = joy$freq, min.freq = 5, max.words = 100, random.order = T, colors = brewer.pal(8,"Accent"))

wordcloud2(joy, size=1.2, shape='diamond') %>% htmlwidgets::prependContent(htmltools::tags$h1("Wordcloud - 21MIC0065")) 

Wordcloud - 21MIC0065

joy %>% top_n(15)%>% mutate(word=reorder(word,freq)) %>% ggplot(aes(x=word, y=freq)) + geom_col() +labs(title="Frequency plot of joywords - 21MIC0065", x= "Joy_words", y="Frequency")

## Selecting by freq

joy %>% top_n(15)%>% mutate(word=reorder(word,freq)) %>% ggplot(aes(x=word, y=freq)) + geom_col() + coord_flip() + labs(title="Frequency plot of joywords - 21MIC0065", x= "Joy_words", y="Frequency")

## Selecting by freq