Introduction

This report applies the tidy text methods from Sections 1.1-1.3 of Text Mining with R to the five customer comments provided in the assignment. The goal is to organize the text, remove common stop words, and identify frequently mentioned words. These comments are an instructional sample, so the results do not represent all customers.

1. Create the dataset

Initially, each row contains a complete comment. A comment ID keeps track of the source of each word during analysis.

comments <- tibble(
  comment_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."
  )
)

knitr::kable(comments, caption = "The five comments supplied in the assignment")
The five comments supplied in the assignment
comment_id 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.

2. Convert the comments to tidy text

The unnest_tokens() function splits the comments into individual words, converts them to lowercase, and removes punctuation. Each row now contains one word from one comment.

tidy_comments <- comments %>%
  unnest_tokens(word, text)

knitr::kable(head(tidy_comments, 20),
             caption = "First 20 word tokens before stop-word removal")
First 20 word tokens before stop-word removal
comment_id word
1 i
1 love
1 the
1 quality
1 of
1 this
1 product
1 the
1 price
1 is
1 reasonable
1 and
1 delivery
1 was
1 fast
2 the
2 product
2 quality
2 is
2 excellent

3. Remove stop words and count words

Stop words are common words such as “the,” “and,” and “is.” Removing them helps highlight words that describe the product and customer experience. The original comments remain available for interpreting context.

clean_comments <- tidy_comments %>%
  anti_join(stop_words, by = "word")

word_counts <- clean_comments %>%
  count(word, sort = TRUE) %>%
  arrange(desc(n), word)

knitr::kable(word_counts, col.names = c("Word", "Frequency"),
             caption = "Word frequencies after stop-word removal")
Word frequencies after stop-word removal
Word Frequency
product 4
delivery 2
excellent 2
fast 2
price 2
quality 2
service 2
beautiful 1
customer 1
expensive 1
friends 1
love 1
purchase 1
reasonable 1
recommend 1
satisfied 1
shipping 1
word_counts %>%
  filter(n >= 2) %>%
  ggplot(aes(x = n, y = reorder(word, n))) +
  geom_col(fill = "steelblue") +
  scale_x_continuous(breaks = seq(0, max(word_counts$n), by = 1)) +
  labs(
    title = "Words Appearing at Least Twice",
    subtitle = "Five customer comments, with stop words removed",
    x = "Number of occurrences",
    y = NULL
  ) +
  theme_minimal(base_size = 12)

Findings

After removing stop words, “product” was the most frequent word, appearing four times, while “quality,” “price,” “delivery,” “fast,” “excellent,” and “service” each appeared twice. Reading the original comments alongside these counts shows praise for quality, service, and fast delivery, along with concerns about high prices and slow shipping; word counts alone do not measure sentiment.

Challenge and solution

One challenge in this analysis is that common words can distract from the main topics in the comments. I addressed this by using anti_join(stop_words, by = "word") to remove them before counting word frequencies.

Source

Silge, J., & Robinson, D. Text Mining with R: A Tidy Approach, Chapter 1, Sections 1.1-1.3. https://www.tidytextmining.com/tidytext

Dataset: Five customer comments supplied in the assignment.