In this lab, I used R to analyze five customer reviews and identify common words and customer opinions.
library(tidytext)
library(dplyr)
library(ggplot2)
reviews <- data.frame(
id = 1:5,
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."
)
)
reviews
## id
## 1 1
## 2 2
## 3 3
## 4 4
## 5 5
## text
## 1 I love the quality of this product. The price is reasonable, and delivery was fast.
## 2 The product quality is excellent, but the shipping took too long.
## 3 Great customer service! I would definitely recommend this product to my friends.
## 4 The price is too expensive. However, the product looks beautiful.
## 5 Fast delivery and excellent service. I am very satisfied with my purchase.
words <- reviews %>%
unnest_tokens(word, text)
head(words)
## id word
## 1 1 i
## 2 1 love
## 3 1 the
## 4 1 quality
## 5 1 of
## 6 1 this
clean_words <- words %>%
anti_join(stop_words, by = "word")
head(clean_words)
## id word
## 1 1 love
## 2 1 quality
## 3 1 product
## 4 1 price
## 5 1 reasonable
## 6 1 delivery
word_count <- clean_words %>%
count(word, sort = TRUE)
word_count
## word n
## 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
word_count %>%
slice_max(n, n = 10, with_ties = FALSE) %>%
ggplot(aes(x = reorder(word, n), y = n)) +
geom_col(fill = "steelblue") +
coord_flip() +
labs(
title = "Most Common Words",
x = "Words",
y = "Frequency"
) +
theme_minimal()
sentiment <- words %>%
inner_join(get_sentiments("bing"), by = "word") %>%
count(sentiment)
sentiment
## sentiment n
## 1 negative 1
## 2 positive 10
tfidf <- clean_words %>%
count(id, word) %>%
bind_tf_idf(word, id, n)
head(arrange(tfidf, desc(tf_idf)), 10)
## id word n tf idf tf_idf
## 1 2 shipping 1 0.2500000 1.609438 0.4023595
## 2 4 beautiful 1 0.2500000 1.609438 0.4023595
## 3 4 expensive 1 0.2500000 1.609438 0.4023595
## 4 3 customer 1 0.2000000 1.609438 0.3218876
## 5 3 friends 1 0.2000000 1.609438 0.3218876
## 6 3 recommend 1 0.2000000 1.609438 0.3218876
## 7 5 purchase 1 0.1666667 1.609438 0.2682397
## 8 5 satisfied 1 0.1666667 1.609438 0.2682397
## 9 1 love 1 0.1428571 1.609438 0.2299197
## 10 1 reasonable 1 0.1428571 1.609438 0.2299197
The word “product” appeared most often in the reviews. Most feedback was positive, but some customers mentioned high prices and slow shipping.
One challenge was removing unnecessary words. I used
anti_join(stop_words) to clean the reviews and focus on
important words.