R_Sentiment_Analyze.Rmd

 

```{r}
# FIRST OF ALL WE INSTALL THAT PACKAGE AND WE CALL SENTIMENT.SENTIMENT DATASET INCLUDE POSITIVE AND NEGATIVE WORD.

install.packages("tidytext")

library(tidytext)

sentiments



```


```{r}
# BING CLASSIFY WORD AS POSITIVE AND NEGATIVE
get_sentiments("bing")

```


```{r}
library(janeaustenr)
library(stringr)

# FIRST OF ALL WE INCLUDE IMPORT LIBRARIES AND WE TİDY OPERATION WİTH PIPING IN TEXT.
# WE CONVERT TEXT INTO TO TİDY FORMAT
#EACH ROW CONTAIN SINGLE WORD PROVIDE ROW NUMBER FUNCTION.
#GROUP BY AUSTEN BOOKS
#FINALLY WITH REGULAR EXPRESSION WE STRING MANIPULATION

 tidy_data <- austen_books() %>%
  group_by(book) %>%
  mutate(linenumber=row_number(),
         chapter=
  cumsum(str_detect(text,
  regex("^chapter [\\divxlc]",
        
  ignore_case = TRUE)))) %>%
   ungroup() %>%
   unnest_tokens(word,text)
```


```{r}

# FIRST OF ALL WE CALL WORD BING.BING CLASSIFY TEXT AS POSITIVE AND NEGATIVE
# AFTERTHAT WE JUST TAKE POSITIVE WORD IN TEXT
#WE CHOOSE EMMA BOOK AND WE SORT POSİTİVE WORD IN EMMA BOOKS

positive_senti <-get_sentiments("bing") %>%
  filter(sentiment=="positive")

tidy_data %>%
  filter(book=="Emma") %>%
  semi_join(positive_senti) %>%
  count(word,sort=TRUE)


```


```{r}

# FIRST OF ALL SPREAD FUNC PROVIDE EXIT TWO UNIQUE COLUMNS AND THAT OPERATE LIKE GROUP BY THINKING
#SHORTL,WE CALCULATE TOTAL SENTIMENT AND THE GROUP BY POSITVE AND NEGATIVE AND SHOW 2 UNIQIE COLUMNS


library(tidyr)
bing <- get_sentiments("bing")
Emma_sentients <- tidy_data %>%
  inner_join(bing) %>%
  count(book="Emma",index=linenumber %/% 80,sentiment) %>%
  spread(sentiment,n,fill=0) %>%
  mutate(sentiment=positive-negative)

```


```{r}
#WE VISUALIZE WORD IN EMMA WITH POSITIVE AND NEGATIVE SCORES

library(ggplot2)

ggplot(Emma_sentients,aes(index,sentiment,fill=book))+
  geom_bar(stat="identity",show.legend = TRUE)+
  facet_wrap(~book,ncol=2,scales="free_x")









```


```{r}
#  MOST COMMON WORD THAT USE EMMA BOOK WE SORT THAT
# WE CALL 5 ROW WITH HEAD FUNC
counting_words <- tidy_data %>%
  inner_join(bing) %>%
  count(word,sentiment,sort=TRUE)
head(counting_words)

```

```{r}
#WE VISUALIZE THE SENTIMENT IN EMMA BOOK AS POSITIVE AND NEGATIVE SCORE

counting_words %>%
  filter(n>250) %>%
  mutate(n=ifelse(sentiment=="negative",-n,n)) %>%
  mutate(word=reorder(word,n))%>%
  ggplot(aes(word,n,fill=sentiment))+
  geom_col()+
  coord_flip()+
  labs(y="Sentiment Score")
```


```{r}

#wE PLOT NEGATIVE AND POSITIVE WORD.
#AS TEST SCORE INCREASE,TEXT SHOW MORE BIGGER THAN OTHER

library(reshape2)
library(wordcloud)
tidy_data %>%
  inner_join(bing) %>%
  count(word,sentiment,sort=TRUE) %>%
  acast(word~sentiment,value.var ="n",fill=0) %>%
  comparison.cloud(colors = c("red","blue"),
                   max.words = 60)



```