library(dplyr)
library(tidyr)
library(ggplot2)
library(tidytext)
text <- c("I love the quality of this product. The price is reasonable, and delivery was fast.",
"The product quality is excellent, but the shipping took too long.",
"Great customer service! I would definitely recommend this product to my friends.",
"The price is too expensive. However, the product looks beautiful.",
"Fast delivery and excellent service. I am very satisfied with my purchase.")
text_df <- tibble(review = 1:5, text = text)
text_df
## # A tibble: 5 × 2
## review text
## <int> <chr>
## 1 1 I love the quality of this product. The price is reasonable, and deliv…
## 2 2 The product quality is excellent, but the shipping took too long.
## 3 3 Great customer service! I would definitely recommend this product to m…
## 4 4 The price is too expensive. However, the product looks beautiful.
## 5 5 Fast delivery and excellent service. I am very satisfied with my purch…
tidy_reviews <- text_df %>%
unnest_tokens(word, text)
data(stop_words)
tidy_clean <- tidy_reviews %>%
anti_join(stop_words, by = "word")
tidy_clean %>%
count(word, sort = TRUE)
## # A tibble: 17 × 2
## word n
## <chr> <int>
## 1 product 4
## 2 delivery 2
## 3 excellent 2
## 4 fast 2
## 5 price 2
## 6 quality 2
## 7 service 2
## 8 beautiful 1
## 9 customer 1
## 10 expensive 1
## 11 friends 1
## 12 love 1
## 13 purchase 1
## 14 reasonable 1
## 15 recommend 1
## 16 satisfied 1
## 17 shipping 1
tidy_clean %>%
count(word, sort = TRUE) %>%
mutate(word = reorder(word, n)) %>%
ggplot(aes(n, word)) +
geom_col() +
labs(x = "Count", y = NULL)
review_sentiment <- tidy_reviews %>%
inner_join(get_sentiments("bing"), by = "word") %>%
count(review, sentiment) %>%
pivot_wider(names_from = sentiment, values_from = n, values_fill = 0) %>%
mutate(sentiment = positive - negative)
review_sentiment
## # A tibble: 5 × 4
## review positive negative sentiment
## <int> <int> <int> <int>
## 1 1 3 0 3
## 2 2 1 0 1
## 3 3 2 0 2
## 4 4 1 1 0
## 5 5 3 0 3
ggplot(review_sentiment, aes(factor(review), sentiment)) +
geom_col() +
labs(x = "Review", y = "Net sentiment")
review_tf_idf <- tidy_clean %>%
count(review, word) %>%
bind_tf_idf(word, review, n) %>%
arrange(desc(tf_idf))
review_tf_idf
## # A tibble: 26 × 6
## review word n tf idf tf_idf
## <int> <chr> <int> <dbl> <dbl> <dbl>
## 1 2 shipping 1 0.25 1.61 0.402
## 2 4 beautiful 1 0.25 1.61 0.402
## 3 4 expensive 1 0.25 1.61 0.402
## 4 3 customer 1 0.2 1.61 0.322
## 5 3 friends 1 0.2 1.61 0.322
## 6 3 recommend 1 0.2 1.61 0.322
## 7 5 purchase 1 0.167 1.61 0.268
## 8 5 satisfied 1 0.167 1.61 0.268
## 9 1 love 1 0.143 1.61 0.230
## 10 1 reasonable 1 0.143 1.61 0.230
## # ℹ 16 more rows
The reviews are mostly positive (10 positive words vs. 1 negative). Customers like the product quality, fast delivery and service, but price (“expensive”) and slow shipping are the main complaints.
When I removed stop words before the sentiment analysis, the word “great” was deleted because it is on the stop word list. I fixed this by running sentiment on all the words and only removing stop words for the word counts and tf-idf.