Paper Info
Title
peq : An explainable, specification-based, aspect-oriented product comparator for e-commerce
Abstract
In recent years, product discussion forums have become a rich environment in which consumers and potential adopters exchange views and information. While purchasing a product, consumers often rely on these online reviews of the product for decision-making. Along with the evaluation of the overall quality of each product, reviews also give useful insights for comparison shopping. While comparing, one often has in mind a specific aspect or a set of aspects which are of interest to them. But, comparing products based on different reviews, written by different authors, is not always fair because of the different expertise, expectations and preferences of each author. So, we focus only on comparative sentences, where two entities are compared directly in a single sentence by the review author. Given a set of such comparative sentences, each relating a pair of entities, we intend to provide explainable comparisons based on the specifications of the product and backed by comparative sentences provided by reviewers. We use the feature specifications of the products which are easily available, and learn the importance to be associated with each of them. This helps us in inferring the sentences that discuss these features in order to better explain why a product should be preferred over another.
Year
DOI
Venue
2016
10.1145/2983323.2983901
ACM International Conference on Information and Knowledge Management
Keywords
Field
DocType
comparison mining,explainable comparison,decision support system
Data mining,Ranking,Aspect-oriented programming,Information retrieval,Computer science,Decision support system,Baseline (configuration management),Digital camera,Purchasing,Sentence,E-commerce
Conference
Citations 
PageRank 
References 
1
0.39
7
Authors
3
Name
Order
Citations
PageRank
Abhishek Sikchi110.39
Pawan Goyal263.57
Samik Datta321.79