Towards Automating the Pricing Power of Product Attributes: An Analysis of Online Product Reviews

1
Show me the Money! Deriving the Pricing Power of
Product Features by Mining Consumer Reviews.
Nikolay Archak, Anindya Ghose, Panagiotis
Ipeirotis New York University Stern School of
Business Information Systems Group, IOMS
department
2
Word of Mouse

• Consumer reviews
• Derived from user experience
• Describe different product features
• Provide subjective evaluations of product
  features
• I love virtually everything about this
  camera....except the lousy picture quality. The
  camera looks great, feels nice, is easy to use,
  starts up quickly, and is of course waterproof.
  It fits easily in a pocket and the battery lasts
  for a reasonably long period of time.
• Comment  Was this review helpful to you? 
  (Report this) (Report this)

3
Existing work

• Identifying product features
• Hu, Liu (AAAI, 2004)
• Ghani, Probst, Liu, Krema, Fano (KDD, 2006)
• Scaffidi (2006)
• Sentiment classification
• Das, Chen (2001)
• Turney, Littman (ACL, 2003)
• Dave, Lawrence, Pennock (WWW, 2003)
• Hu, Liu (KDD, 2004)
• Popescu, Etzioni, (EMNLP, 2005)
• Opinion Analysis
• Hu, Liu, Cheng (WWW, 2005)

4
Research Questions

• How important is each product feature to
  customers?
• What is the pragmatic polarity and strength of
  customers opinions?

Sales data provides valuable clues
5
Overview of our Approach

• Examine changes in demand and estimate weights of
  features and strength of evaluations.

excellent lenses
excellent photos
3
6
poor lenses
poor photos
-1
-2

• Feature photos is twice more important than
  lenses
• Excellent is positive, poor is negative
• Excellent is three times stronger than poor

6
Economic background Hedonic goods and hedonic
regressions

• We are not the first to measure weights of
  product features. Economists are doing this for
  years.
• Hedonic goods Rosen, 1974
• Each good is characterized by the set of its
  objectively measured features
• Preferences of consumers are solely determined by
  features of available goods
• Are all goods hedonic?
• Hedonic regressions
• log(CameraPrice) const b1NumMegapixels
  b2Zoom b3StorageSize

7
Hedonic regressions with subjectively measured
features

• Problem traditional hedonic regressions include
  only objectively measured features
• Our solution introduce review evaluations into
  the hedonic framework. Each opinion assigns
  implicit subjective score to a feature We dont
  know the scores.
• For example
• review1 says excellent lenses implicit opinion
  score 0.7 and nice lenses implicit opinion
  score 0.3
• review2 says decent lenses implicit opinion
  score -0.1
• Average score of the lenses feature is
• 0.7 0.3 - 0.1 / 3 0.3

8
Representing consumer review(s)
Evaluations
excellent poor good ej
lenses 0.2 0 0.1 ...
photos 0 0 0.3
ease of use 0 0.4 0
fi Wij
Features
Nx opinion phrase frequency Wx opinion phrase
weight s smoothing factor
Matrix tensor representation allows us
naturally estimate feature weights and evaluation
scores.
9
Our Model
log (Demand) a b log (Price) b1
Megapixels b2 Zoom
?11Wexcellent lenses ?12Wgreat lenses
... ?1MWterrible lenses
?21Wexcellent photos ?22Wgreat
photos ?2MWterrible photos
?N1Wexcellent size ?N2Wgreat size
... ?NMWterrible size
10
Technical Challenge Reduce the Number of
Parameters

• Solution place a rank constraint
• Special case (p 1) independent features
  weights and evaluation scores

11
Amazon.com Dataset
Product Category Audio Video Camera Photo
Number of products 127 115
Number of sales rank observations 35,143 31,233
Number of reviews 2,580 1,955
Period April 2005 May 2006 April 2005 May 2006
12
Results - Feature Weights for Camera Photo
13
Results - Evaluation Coefficients for Camera
Photo
14
Partial effects for Camera Photo
great camera 0.4235 decent battery -0.0139
good camera 0.1128 decent quality -0.0822
great quality 0.0931 poor quality -0.1067
good quality 0.0385 bad camera -0.6547
great battery 0.0138 fine camera -0.677
Partial effect of an opinion phrase score of
the average review where all evaluations of the
feature f are replaced by the evaluation e minus
score of the average review.
15
Predictive power of product reviews

• Goal predict future sales using review text
• Model test 10-fold cross validation (product
  holdout)
• Compared with model that ignores text but keeps
  numeric variables including average review rating
• Average RMSE improvement 5, Avg. Err improvement
  3

16
Conclusions

• We provided technique for
• Measuring importance of product features for
  consumers
• Identifying polarity and strength of user
  evaluations
• Alleviating problem of data sparseness

17
Thank you!

• Comments? Questions?

18
Related Work

• Chevalier, Mayzlin (2006)
• Chevalier, Goolsbee (2003)
• Ghani, Probst, Liu, Krema, Fano (2006)
• Hu, Liu (2004)
• Hu, Liu, Cheng (2005)
• Turney (2002)
• Pang, Lee (2005)
• Popescu, Etzioni (2005)