Amazon Product Data Reviews: The Role of Experiential Framing

Posted on Mar 28, 2021
The skills we demoed here can be learned through taking Data Science with Machine Learning bootcamp with NYC Data Science Academy.

Amazon Product Data Reviews: The Role of Experiential Framing

Shiny App | Github

Background: The Importance of Consumer Reviews

In an era of unprecedented dependence on technological capabilities via the internet and the World Wide Web, companies are pivoting toward enhancement of their online presence in data marketing, sales, and customer service. This has been particularly true since the onset of the Covid-19 pandemic that forced large swaths of human society into their homes and onto their laptops.

Online consumer reviews have become increasingly critical to the success of almost any business. Even before Covid-19, surveys were showing that 84% of consumers trust online customer reviews, while only 25% of consumers trust print and digital ads. The number of positive reviews can increase purchase rates and consumer confidence, making consumer reviews a powerful sales strategy.

Given the importance of positive reviews for consumer products, one important question is: Are all positive reviews treated equally? In other words, are some types of positive reviews more effective than others?

Companies often receive important feedback about their products from negative reviews. What happens when products receive very few negative reviews? Comparing the differences in positive reviews is particularly relevant for products that consistently receive overwhelmingly positive ratings, as is the case with Amazon Product Reviews. As can be seen in the graph below, the Star Ratings for Amazon Products has a left skew, with the vast majority of consumers providing ratings of 4 or 5 stars. Overall, consumers love Amazon products. What types of insights can be derived from analysis of these overwhelmingly positive reviews? 

Data on Experiential Framing

Consumer reviews can emphasize multiple themes, including experience, emotions, or functionality. Experiential framing typically includes a description or portrayal of a product that highlights the action or occasion in which a product is used (e.g., purchased to stay in touch with family while traveling), whereas functionality framing focuses on the product’s features (e.g., “battery life outstanding”).

Studies have shown that experiential framing often elicits emotional responses and is associated with an increase in happiness. Specifically, experiential framing of products can:

  • Improve consumers' evaluation of the product
  • Improve brand loyalty and brand satisfaction
  • Increase the likelihood that a consumer will review the product

Present Data Analysis

The purpose of the present analysis was to:

1) Compare experiential, emotional, and functional framing of Alexa enabled vs. non-Alexa enabled Amazon products in consumer reviews

2) Examine whether experiential and emotional framing in consumer reviews predicts consumer interest in Alexa products

*Experiential and emotional framing might be particularly relevant for Alexa products, given the interactive nature of the product.

The Data

Data Set for Amazon Product Reviews

The data set used for this analysis was provided by Datafiniti's Product Database and consists of 5,000 consumer reviews for Amazon products such as Kindle, Fire TV Stick, and echo from Jan 2016 – Sept 2018. This data includes basic product information, ratings, number of "helpful votes" each review received, and review dates for each product.

Google Trends Data Set

The data also included a Google trends data set for relative frequency of searching for ‘Alexa’ products during the same period as a measure of consumer interest. This data set was joined to the Amazon Product Review data set for further analysis.


The analyses included:

  • Sentiment Analysis (positive vs. negative words) of product reviews
  • Natural Language Processing to identify reviews containing Experiential vs. Emotional vs. Functional word types
  • Multiple Regression to investigate changes in Ratings as a function of Word Type
  • Annual Trends for Experiential/Emotional/Functional Framing
  • Annual Trends for Consumer Interest (via Google Search trends)
  • Correlation analyses examining the Relationship between Experiential/Emotional/Functional Framing and Consumer Interest

Insights from these analyses can also be examined via this R Shiny app.

Sentiment Analysis

As stated above, it is clear that consumers love Amazon products, with the vast majority of consumers providing 4 and 5 star ratings. In addition, a sentiment analysis showed that consumers use substantially more positive words than negative words in the review text (see figure below).

Amazon Product Data Reviews: The Role of Experiential Framing

Natural Language Processing: Word Type Examples

Reviews containing experiential framing were identified using key words that described the context in which products were used and/or the way in which the product impacted daily life, such as communicate/talk, fun, daily, educational, information, entertainment, helpful, travel, home, and morning.

"Like having another person in the house, I talk to Alexa more [than] my wife"

Reviews containing emotional framing were identified using key words such as love, happy, enjoy, satisfied, and excited.

Reviews containing functionality framing were identified using key words such as user friendly, feature, battery, setup, and durable.

Multiple Regression Analyses: Changes in Ratings as a Function of Word Type

Multiple regression analyses showed that the number of experiential words in Amazon product reviews significantly predicted positive star ratings (see Figure 1 below). This pattern was only evident for Alexa enabled products. Emotion words predicted positive star ratings for both Alexa enabled and non-Alexa products. Functionality words did not predict positive star ratings for Alexa enabled products (see Figure 2 below), but did predict star ratings for non-Alexa products.

Figure 1. Experience words predicted positive star ratings for Alexa enables products.

Amazon Product Data Reviews: The Role of Experiential Framing

Figure 2. Functionality words did not predict positive star ratings for Alex enables products.

Annual Data Trends 

The number of experiential words in Amazon product reviews increased from January 2016 to July 2018.

The number of Google searches for Amazon products also increased during this time period:

When combined, Pearson’s r correlation analyses show that the number of experiential words over time is positively correlated with the number of Google searches for Amazon products over time (r = .17):

The correlation for number of emotion and number of Google searches for Amazon products is substantially weaker (r = .07):

In contrast to findings for experiential words, the number of functionality words is negatively correlated with number of Google searches (r = -.14):

Shiny App

All of these findings can be examined in more detail here in this R Shiny App:


Conclusions and Recommendations

  • It is clear that consumers love Amazon products
  • In spite of overwhelmingly positive reviews for Amazon products, there is still variability in reviews and consumer interest, and these differences are predicted by differences in experiential vs. functionality framing of products
  • Amazon should highlight experiential and emotional consumer reviews as part of a marketing strategy, especially for Alexa-enabled products

Future Work

  • More recent review data is needed to examine continuing trends
  • Future analyses should mitigate the potential influence of bots and fake reviews by focusing on analysis of reviews provided by verified users
  • A more precise analysis of the relationship between experiential reviews and consumer behaviors would include examination of click streams and purchase behavior, which would address the following important question: Are consumers more likely to purchase the product after reading a review that includes experiential and/or emotional framing?

And finally, perhaps the most interesting question: What is the future of Alexa enabled products in our daily life? As Amazon products continue to expand in ways that make our lives more connected and convenient, we will patiently await the day when we can finally say: Alexa, fold my laundry.


About Author

Sara Kien

As a social science researcher with a PhD in cognitive psychology, Sara has been applying data science skills (including hypothesis testing, statistics, machine learning, and natural language processing) to program evaluation and behavioral science in ways that enhance...
View all posts by Sara Kien >

Leave a Comment

No comments found.

View Posts by Categories

Our Recent Popular Posts

View Posts by Tags

#python #trainwithnycdsa 2019 2020 Revenue 3-points agriculture air quality airbnb airline alcohol Alex Baransky algorithm alumni Alumni Interview Alumni Reviews Alumni Spotlight alumni story Alumnus ames dataset ames housing dataset apartment rent API Application artist aws bank loans beautiful soup Best Bootcamp Best Data Science 2019 Best Data Science Bootcamp Best Data Science Bootcamp 2020 Best Ranked Big Data Book Launch Book-Signing bootcamp Bootcamp Alumni Bootcamp Prep boston safety Bundles cake recipe California Cancer Research capstone car price Career Career Day citibike classic cars classpass clustering Coding Course Demo Course Report covid 19 credit credit card crime frequency crops D3.js data data analysis Data Analyst data analytics data for tripadvisor reviews data science Data Science Academy Data Science Bootcamp Data science jobs Data Science Reviews Data Scientist Data Scientist Jobs data visualization database Deep Learning Demo Day Discount disney dplyr drug data e-commerce economy employee employee burnout employer networking environment feature engineering Finance Financial Data Science fitness studio Flask flight delay gbm Get Hired ggplot2 googleVis H20 Hadoop hallmark holiday movie happiness healthcare frauds higgs boson Hiring hiring partner events Hiring Partners hotels housing housing data housing predictions housing price hy-vee Income Industry Experts Injuries Instructor Blog Instructor Interview insurance italki Job Job Placement Jobs Jon Krohn JP Morgan Chase Kaggle Kickstarter las vegas airport lasso regression Lead Data Scienctist Lead Data Scientist leaflet league linear regression Logistic Regression machine learning Maps market matplotlib Medical Research Meet the team meetup methal health miami beach movie music Napoli NBA netflix Networking neural network Neural networks New Courses NHL nlp NYC NYC Data Science nyc data science academy NYC Open Data nyc property NYCDSA NYCDSA Alumni Online Online Bootcamp Online Training Open Data painter pandas Part-time performance phoenix pollutants Portfolio Development precision measurement prediction Prework Programming public safety PwC python Python Data Analysis python machine learning python scrapy python web scraping python webscraping Python Workshop R R Data Analysis R language R Programming R Shiny r studio R Visualization R Workshop R-bloggers random forest Ranking recommendation recommendation system regression Remote remote data science bootcamp Scrapy scrapy visualization seaborn seafood type Selenium sentiment analysis sentiment classification Shiny Shiny Dashboard Spark Special Special Summer Sports statistics streaming Student Interview Student Showcase SVM Switchup Tableau teachers team team performance TensorFlow Testimonial tf-idf Top Data Science Bootcamp Top manufacturing companies Transfers tweets twitter videos visualization wallstreet wallstreetbets web scraping Weekend Course What to expect whiskey whiskeyadvocate wildfire word cloud word2vec XGBoost yelp youtube trending ZORI