Introduction

This analysis uses the tidytext approach to examine a small sample of social media customer comments. The goal is to identify commonly used words and better understand the major themes appearing in customer feedback.

# Install packages only if they are not already installed
packages <- c("tidyverse", "tidytext")

new_packages <- packages[!(packages %in% installed.packages()[,"Package"])]

if(length(new_packages) > 0) {
  install.packages(new_packages)
}

# Load packages
library(tidyverse)
library(tidytext)

1. Create the Social Media Dataset

The dataset contains five sample customer comments discussing product quality, price, delivery, and customer service.

social_media <- tibble(
  post_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."
  )
)

social_media
## # A tibble: 5 × 2
##   post_id text                                                                  
##     <int> <chr>                                                                 
## 1       1 I love the quality of this product. The price is reasonable, and deli…
## 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 …
## 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 purc…

2. Convert the Text into a Tidy Format

Following the tidy text format, each individual word is converted into its own row using unnest_tokens().

tidy_posts <- social_media %>%
  unnest_tokens(word, text)

tidy_posts
## # A tibble: 60 × 2
##    post_id word   
##      <int> <chr>  
##  1       1 i      
##  2       1 love   
##  3       1 the    
##  4       1 quality
##  5       1 of     
##  6       1 this   
##  7       1 product
##  8       1 the    
##  9       1 price  
## 10       1 is     
## # ℹ 50 more rows

This creates a one-token-per-row structure, making it easier to analyze individual words across all five comments.

3. Remove Stop Words

Common words such as “the,” “is,” “and,” and “with” usually provide little information about the main themes of a text. These stop words can be removed using the stop_words dataset from the tidytext package.

tidy_posts_clean <- tidy_posts %>%
  anti_join(stop_words, by = "word")

tidy_posts_clean
## # A tibble: 26 × 2
##    post_id word      
##      <int> <chr>     
##  1       1 love      
##  2       1 quality   
##  3       1 product   
##  4       1 price     
##  5       1 reasonable
##  6       1 delivery  
##  7       1 fast      
##  8       2 product   
##  9       2 quality   
## 10       2 excellent 
## # ℹ 16 more rows

4. Count the Most Common Words

Next, the remaining words are counted and sorted from most frequent to least frequent.

word_counts <- tidy_posts_clean %>%
  count(word, sort = TRUE)

word_counts
## # 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

5. Visualize the Most Common Words

The bar chart below displays the most frequently occurring meaningful words in the customer comments.

word_counts %>%
  filter(n >= 1) %>%
  slice_max(n, n = 15, with_ties = FALSE) %>%
  mutate(word = reorder(word, n)) %>%
  ggplot(aes(x = word, y = n)) +
  geom_col(fill = "steelblue") +
  coord_flip() +
  labs(
    title = "Most Common Words in Customer Comments",
    x = "Word",
    y = "Frequency"
  ) +
  theme_minimal()

6. Sentiment Analysis

The Bing sentiment lexicon classifies words as either positive or negative. This allows us to examine the overall sentiment expressed in the customer comments.

bing_sentiments <- get_sentiments("bing")

sentiment_words <- tidy_posts_clean %>%
  inner_join(bing_sentiments, by = "word")

sentiment_words
## # A tibble: 10 × 3
##    post_id word       sentiment
##      <int> <chr>      <chr>    
##  1       1 love       positive 
##  2       1 reasonable positive 
##  3       1 fast       positive 
##  4       2 excellent  positive 
##  5       3 recommend  positive 
##  6       4 expensive  negative 
##  7       4 beautiful  positive 
##  8       5 fast       positive 
##  9       5 excellent  positive 
## 10       5 satisfied  positive

7. Positive vs. Negative Words

sentiment_counts <- sentiment_words %>%
  count(sentiment)

sentiment_counts
## # A tibble: 2 × 2
##   sentiment     n
##   <chr>     <int>
## 1 negative      1
## 2 positive      9
sentiment_counts %>%
  ggplot(aes(x = sentiment, y = n, fill = sentiment)) +
  geom_col(show.legend = FALSE) +
  labs(
    title = "Sentiment of Customer Comments",
    x = "Sentiment",
    y = "Number of Words"
  ) +
  theme_minimal()

8. Sentiment by Post

The following analysis compares the number of positive and negative words found in each individual customer comment.

post_sentiment <- sentiment_words %>%
  count(post_id, sentiment)

post_sentiment
## # A tibble: 6 × 3
##   post_id sentiment     n
##     <int> <chr>     <int>
## 1       1 positive      3
## 2       2 positive      1
## 3       3 positive      1
## 4       4 negative      1
## 5       4 positive      1
## 6       5 positive      3
post_sentiment %>%
  ggplot(aes(
    x = factor(post_id),
    y = n,
    fill = sentiment
  )) +
  geom_col(position = "dodge") +
  labs(
    title = "Positive and Negative Sentiment by Post",
    x = "Post ID",
    y = "Number of Sentiment Words",
    fill = "Sentiment"
  ) +
  theme_minimal()

Findings

The text analysis shows that customer comments focus primarily on product quality, price, delivery, and service. Positive words such as love, excellent, great, beautiful, satisfied, and recommend indicate that customers generally express favorable opinions about the product and their experiences.

However, some negative feedback is also present. In particular, customers mention that the product can be expensive and that shipping can take too long. Overall, the sample suggests generally positive customer sentiment, while price and shipping speed represent potential areas for improvement.

Conclusion

Using the tidytext framework makes it possible to transform unstructured social media comments into data that can be analyzed quantitatively. Word-frequency and sentiment analysis help identify common customer concerns and provide businesses with insights into what customers value and what aspects of the customer experience may need improvement.