Estimating the Helpfulness and Economic Impact of Product Reviews: Mining Text and Reviewer Characteristics
read more
Citations
Sentiment Analysis and Opinion Mining
A survey on opinion mining and sentiment analysis
Social Media Brand Community and Consumer Behavior: Quantifying the Relative Impact of User- and Marketer-Generated Content
What makes a useful online review? Implication for travel product websites
What can big data and text analytics tell us about hotel guest experience and satisfaction
References
Random Forests
Econometric Analysis of Cross Section and Panel Data
A Tutorial on Support Vector Machines for Pattern Recognition
Mining and summarizing customer reviews
Thumbs up? Sentiment Classification using Machine Learning Techniques
Related Papers (5)
Examining the Relationship Between Reviews and Sales: The Role of Reviewer Identity Disclosure in Electronic Markets
Research Note: What Makes a Helpful Online Review? A Study of Customer Reviews on Amazon.com
Frequently Asked Questions (9)
Q2. What have the authors stated for future works in "Estimating the helpfulness and economic impact of product reviews: mining text and reviewer characteristics" ?
Future work can look at real demand data. The actual magnitude of the impact of textual information on sales may be different for a different retailer. Additional work in other on-line contexts will be needed to evaluate whether review text information has similar explanatory power that are similar to those the authors have obtained. Furthermore, the helpfulness of a review may be influenced by the way that reviews are presented to different types of users [ 58 ] and by the context in which a user evaluates a given review [ 59 ].
Q3. What is the common criterion for the addition or deletion of variables in stepwise?
The most commonly used criterion for the addition or deletion of variables in stepwise regression is based on the partialF − statistic for each of the regressions which allows one to compare any reduced (or empty) model to the full model from which it is reduced.
Q4. What is the effect of subjectivity on reviews?
In terms of subjectivity and its effect on helpfulness, the authors observe that for feature-based goods, such as electronics, users prefer reviews that contain mainly objective information with only a few subjective sentences and rate those higher.
Q5. What is the way to mark reviews that have helpfulness?
Since Helpfulness goes from 0 to 1, the authors can simply select a threshold τ , and mark all reviews that have helpfulness ≥ τ as helpful and the others as not helpful.
Q6. What is the dependent variable of the log of sales rank of a product?
The dependent variable is ln(SalesRank)kt, the log of sales rank of product k in time t, which is a linear transformation of the log of product demand, as discussed earlier.
Q7. What is the ln(D) of the log of sales rank?
Based on this observation, it is possible to convert sales ranks into demand levels using the following Pareto relationship:ln(D) = a+ b · ln(S) (1) where D is the unobserved product demand, S is its observed sales rank, and a > 0, b < 0 are industry-specific parameters.
Q8. What are the three potential constructs for text-based features that are likely to have an impact?
Keeping these in mind, the authors formulate three potential constructs for text-based features that are likely to have an impact: (i) the average level of subjectivity and the range and mix of subjective and objective comments, (ii) the extent to whichthe content is easy to read, and (iii) the proportion of spelling errors in the review.
Q9. What is the effect of a higher readability score on reviews?
The authors also find that for audio-video players and DVDs, a higher readability score Readability is associated with a higher percentage of helpful votes.