保留正文与补采附件。源页面当前未重新核验；具体限制见交付清单。

Revisit consent button We value your privacy We use cookies to enhance your browsing experience, serve personalised ads or content, and analyse our traffic. By clicking "Accept All", you consent to our use of cookies. Customise Reject All Accept All Customise Consent Preferences We use cookies to help you navigate efficiently and perform certain functions. You will find detailed information about all cookies under each consent category below. The cookies that are categorised as "Necessary" are stored on your browser as they are essential for enabling the basic functionalities of the site. ... Show more NecessaryAlways Active Necessary cookies are required to enable the basic features of this site, such as providing secure log-in or adjusting your consent preferences. These cookies do not store any personally identifiable data.

Functional Functional cookies help perform certain functionalities like sharing the content of the website on social media platforms, collecting feedback, and other third-party features.

Analytics Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics such as the number of visitors, bounce rate, traffic source, etc.

Performance Performance cookies are used to understand and analyse the key performance indexes of the website which helps in delivering a better user experience for the visitors.

Advertisement Advertisement cookies are used to provide visitors with customised advertisements based on the pages you visited previously and to analyse the effectiveness of the ad campaigns.

Uncategorised Other uncategorised cookies are those that are being analysed and have not been classified into a category as yet. No cookies to display. Reject All Save My Preferences Accept All Toggle SearchToggle Mobile Navigation Publish AI, ML & data-science insights to a global community of data professionals. Sign inSubmit an Article LatestEditor's PicksNewsletterShipAI

Write For TDS LinkedInXToggle Search Data Science

Customer Satisfaction Measurement with N-gram and Sentiment Analysis

Product reviews are an excellent source of information for qualified management decisions. Learn more about the right text mining... Petr Koráb April 10, 20237 min read

Product reviews are an excellent source of information for qualified management decisions. Learn more about the right text mining techniques.

Photo by Freepik on Freepik Photo by Freepik on Freepik Learn this step by step with the interactive AI and Data Scientist roadmap.

Introduction

Happy customers drive company growth. The five-word sentence explains everything about why we do our best to maximize customer satisfaction. Product reviews are one of the major data sources that large companies like Amazon and Apple, middle-sized exporters including Lentiamo, and local companies running their Facebook pages collect. Reviews are typically collected repeatedly over time, and factors like quality shifts, marketing communications, and customer care friendliness impact the sentiment expressed by customers. Note: Image by author, based on the review of Karim 2011, Baker and Wurgler 2006, Merrin et al. 2013, and Eachempat et al. 2022 Note: Image by author, based on the review of Karim (2011), Baker and Wurgler (2006), Merrin et al. (2013), and Eachempat et al. (2022) The Business Intelligence (BI) role should be to analyze product reviews, identify potential problems, and develop hypotheses to solve them. In the next stage, these recommendations are scrutinized by other departments based on the company structure. This article will explain more closely the analytics of customer satisfaction measurement with product reviews data. The-end-to end process includes:

We'll work in Python, which most BI and data analysts routinely use.

2. Data

Getting unscraped product reviews data with a flexible data license is generally difficult. Synthetic data from Fake Reviews Dataset distributed with Attribution 4.0 International license is an excellent option in this case. The data looks like this: Image 1. Fake Reviews Dataset Image 1. Fake Reviews Dataset The text column contains product reviews, and period marks the review date. The subset we'll work with contains 3848 reviews of clothing, shoes, and jewelry products.

3. Exploratory data analysis (EDA)

EDA in this type of dataset should discover the completeness of the dataset for each period of interest and the presence of noise that does not bring valuable information – digits and special characters. We try to avoid the situation of highly imbalanced datasets containing very few reviews in some periods and noisy datasets with too many digits and special characters (/, @, &,;, ? etc.). 3.1. Checking for data completeness First, let's check the data for completeness for each period. We make annual comparisons and therefore summarise the reviews for each year: python

import pandas as pd

# Calculate review frequencies by year
data['year'] = pd.DatetimeIndex(data['period']).year
rows_count = data.groupby('year', as_index=False).year.value_counts()
rows_count.columns=['year','reviews']

import matplotlib.pyplot as plt

# Generate a line plot
rows_count.plot.line(x='year',y = 'reviews')
plt.show()

A simple line pot shows the yearly review frequencies. It is not necessary to make any graph formatting here: Image 2. Yearly product review frequencies. Image by author. Image 2. Yearly product review frequencies. Image by author.

The dataset is not largely imbalanced. We have about 200 and more reviews per year, which makes a solid dataset for sentient and n-gram analyses. 3.2. Calculating letter-to-other characters ratio Next, let's check if the data does not consist mainly of numbers and special characters, which could bias later text mining procedures. python

import re

# Convert product reviews to a string
text = pd.Series.to_string(data['text'], index = False)

# Remove newline characters
text = re.sub('n', '', text)

# Calculate sum of numbers, letters, and spaces
numbers = sum(c.isdigit() for c in text)
letters = sum(c.isalpha() for c in text)
spaces  = sum(c.isspace() for c in text)
others  = len(text) - numbers - letters - spaces

We calculate cleanness and dirtiness (the opposite) metrics that show the ratios of letters to other characters (numbers, spaces, and special characters): python

# Calculate metrics
dirtiness = ((numbers + others) / len(text)) * 100
cleanness = ((letters + spaces) / len(text)) * 100

print(dirtiness)
print(cleanness)

The print output is:

We have around 9 % of digits and special characters in the data. This volume of noise should not bias sentiment analysis in the later stage.

4. Customer satisfaction measurement

Text mining attempts to find out: (1) how the customers' sentiment developed over time and (2) which factors contributed to changes in customer satisfaction. We'll use Arabica, a Python library for time-series text mining, to explore both. EDIT Jul 2023 : Arabica has been updated. Check the documentation for the full list of parameters.

4.1. Sentiment analysis

Arabica offers coffee_break module for sentiment and breakpoint analysis. Its documentation provides more details about the models and methodology of sentiment evaluation. This code cleans data from punctuation and numbers, removes other redundant strings ("
", "/n", and "Another Long String" are used as examples), calculates sentiment for each review, aggregates the sentiment by year, and identifies two major break points in the sentiment time series: python

from arabica import coffee_break

coffee_break(text = data['text'],
             time = data['period'],
             date_format = 'us',     # Use US-style date format to read dates
             preprocess = True,      # Clean data - digits and punctuation
             skip = ['<br />',       # Remove additional stop words
                     '/n',
             'Another Long String'],
             n_breaks = 2,           # 2 breakpoints identified
             time_freq = 'Y')        # Yearly aggregation

The line plot with sentiment and breakpoints: Image 3. Sentiment analysis with breakpoints. Image by author. Image 3. Sentiment analysis with breakpoints. Image by author. We can see fluctuations in sentiment over time. These changes are not rapid as sentiment varies [0.6: 0.7]. The higher value of sentiment, the better customers perceive the products (and the opposite).

In 1991 and 2000, there were positive and negative breakpoints in sentiment. In the next stage, let's check what caused these shifts.

4.2. Factors driving customer satisfaction

We'll use a heatmap of n-gram-frequencies from the cappuccino module to visually derive the factors that influenced customers' sentiment. Read the documentation for more technical details. This code plots a heatmap of the eight most frequent bigrams (i.e., two consecutive words) in each year. The data pre-processing includes cleaning from English stopwords, numbers, and three unwanted strings ("
", "/n" , and "Another Long String"). Punctuation and blank rows are removed automatically: python

from arabica import cappuccino

cappuccino(text = data['text'],
           time = data['period'],
           date_format = 'us',       # Use US-style date format to parse dates
           plot = 'heatmap',
           ngram = 2,                # N-gram size, 1 = unigram, 2 = bigram
           time_freq = 'Y',          # Aggregation period, 'M' = monthly, 'Y' = yearly
           max_words = 8,            # Display 8 most frequent bigrams for each period
           stopwords = ['english'],  # Remove English stopwords
           skip = ['<br />',         # Remove additional stop words
                   '/n',
           'Another Long String'],
           numbers = True,           # Remove numbers
           lower_case = True)        # Lowercase text

The bigram heatmap: Image 4. Bigram heatmap. Image by author. Image 4. Bigram heatmap. Image by author. Bigram frequencies indicate that:

Conclusions

This type of text-mining analytics should help make qualified data-informed decisions and improve the quality of our products and services. Based on the analytical results, we determine a set of hypotheses about what might be wrong and where is space for improvement. From the text mining analysis in this article, we can see potential problems with product quality. The products fit worse our customers' current needs. Receiving the reviews in 2001, the analysts should formulate a set of problem hypotheses such as:

Many other potential problem hypotheses arise since you know your products better than anyone else. Other departments (Marketing, Customer Care, Logistics, ..) should find out where the problem is, then react with specific improvements, and fix the problem. The response, of course, depends on the company's size and structure and other firm-specific factors. The jupyter notebook with the code and data is on my GitHub. Did you like the article? You can invite me for coffee and support my writing. You can also subscribe to my email list to get notified about my new articles. Thanks!

References

Baker, M., Wurgler, J., 2006. Investor sentiment and the cross-section of stock returns. Journal of Finance 61 (4). Eachempati, P., Srivastava, P. R., Kumar A., Munoz, J., Dursun D., 2022. Can customer sentiment impact firm value? An integrated text mining approach. Technological Forecasting & Social Change 174 (1). Karim, B., 2011. Corporate name change and shareholder wealth effect: empirical evidence in the French stock market. Journal of Asset Management 12 (3). Merrin, R. P., Hoffmann, A. O., Pennings, J. M., 2013. Customer satisfaction as a buffer against sentimental stock-price corrections. Marketing Letters 24 (1).

Register Now to Continue Reading

Unlock Towards Data Science with a Free Account

All articles on Towards Data Science are available to registered users. Create a free account today to access this article and thousands more. Register for freeSign in to your account

Written By

Petr Koráb

See all from Petr Koráb Business IntelligenceData SciencePythonSentiment AnalysisText Mining Share This Article

Towards Data Science is a community publication. Submit your insights to reach our global audience and earn through the TDS Author Payment Program. Write for TDS

Related Articles

Deploying Machine Learning Models with Heroku

Artificial Intelligence Don't just train, but also deploy: a step-by-step guide Avi Chawla September 10, 20228 min read

How to build decision intelligence software

Artificial Intelligence Four lessons from launching my first product Cameron Afzal September 10, 20209 min read

From Messy to Neat with Python Pandas

Artificial Intelligence A practical tutorial Soner Yıldırım March 18, 20214 min read

This is How I Create Dazzling Dashboards Purely in Python.

Programming Plotly dash apps are the fastest way to build production-grade dashboards in python. Thuwarakesh Murallie September 5, 20216 min read

Where people are most interested in Data Visualization and Data Science

Data Science Today I extracted Google Trends data using R to find cities with most searches in 'Data Visualization' and 'Data science' as well as... Hannah Yan Han September 9, 20173 min read

Plotting Maps with GeoPandas

Beginners Guide to Geospatial Data Plotting Ryan Lewis March 14, 20215 min read

Five essential things you must know to learn Tableau

Data Science A guide with free resources for building your skills Brian Perron, PhD June 9, 20225 min read

3 Tips You Need to Be Successful in Data Visualization

Programming Your data is good - but you can make it better. Benjamin Nweke May 18, 20226 min read

How to Get Into Data Science Without a Degree

Programming Advice from a Data Scientist in the same position Terence Shin, MSc, MBA October 29, 20207 min read

Your home for data science and AI. The world's leading publication for data science, data analytics, data engineering, machine learning, and artificial intelligence professionals. Subscribe to Our NewsletterWrite For TDS•About•Advertise•Privacy Policy•Terms of Use © Insight Media Group, LLC 2026•The New Stack•roadmap.sh•Creator Network

Recommended Articles

Close