CAPRA: a comprehensive approach to product ranking using customer reviews
ComputingPublished 23 February 2015
Erfan Najmi, Khayyam Hashmi, Zaki Malik, Abdelmounaam Rezgui, Habib Ullah Khan
Citations82
SJR quartileQ1
SJR score0.88
SNIP1.37
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A product ranking system that facilitates the online shopping experience by analyzing the reviews for sentiments, evaluating their usefulness, extracting and weighing different product features and aspects, ranking it among similar comparable products, and finally creating a unified rank for each product is proposed.
Abstract
Online shopping generates billions of dollars in revenues, including both the physical goods and online services. Product images and associated descriptions are the two main sources of information used by the shoppers to gain knowledge about a product. However, these two pieces of information may not always present the true picture of the product. Images could be deceiving, and descriptions could be overwhelming or cryptic. Moreover, the relative rank of these products among the peers may lead to inconsistencies. Hence, a useful and widely used piece of information is "user reviews". A number of vendors like Amazon have created whole ecosystems around user reviews, thereby boosting their revenues. However, extracting the relevant and useful information out of the plethora of reviews is not straight forward, and is a very tedious job. In this paper we propose a product ranking system that facilitates the online shopping experience by analyzing the reviews for sentiments, evaluating their usefulness, extracting and weighing different product features and aspects, ranking it among similar comparable products, and finally creating a unified rank for each product. Experiment results show the usefulness of our proposed approach in providing an effective and reliable online shopping experience in comparison with similar approaches.
Keywords
Computer Science
Computer Networks and ISDN SystemsThe anatomy of a large-scale hypertextual Web search engine
15,828 Citations1998Sergey Brin, Lawrence M. Page
This paper provides an in-depth description of Google, a prototype of a large-scale search engine which makes heavy use of the structure present in hypertext and looks at the problem of how to effectively deal with uncontrolled hypertext collections where anyone can publish anything they want.
Mining and summarizing customer reviews
7,714 Citations2004Minqing Hu, Bing Liu
This research aims to mine and to summarize all the customer reviews of a product, and proposes several novel techniques to perform these tasks.
College Composition and CommunicationA Comprehensive Grammar of the English Language
5,535 Citations1987P Beauvais, Randolph Quirk +3 more
A Practical Guide to Support Vector Classication
5,069 Citations2008Chih‐Wei Hsu, Chih-Chung Chang +1 more
A simple procedure is proposed, which usually gives reasonable results and is suitable for beginners who are not familiar with SVM.
International Journal of LexicographyIntroduction to WordNet: An On-line Lexical Database<sup>*</sup>
4,207 Citations1990George A. Miller, Richard Beckwith +3 more
Standard alphabetical procedures for organizing lexical information put together words that are spelled alike and scatter words with similar or related meanings haphazardly through the list.
Meeting of the Association for Computational LinguisticsThumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews
3,654 Citations2002Peter Peter, Turney
A sentimental education
3,343 Citations2004Bo Pang, Lillian Lee
A novel machine-learning method is proposed that applies text-categorization techniques to just the subjective portions of the document, which greatly facilitates incorporation of cross-sentence contextual constraints.
Computational LinguisticsLexicon-Based Methods for Sentiment Analysis
3,255 Citations2011Maite Taboada, Julian Brooke +3 more
The Semantic Orientation CALculator (SO-CAL) uses dictionaries of words annotated with their semantic orientation (polarity and strength), and incorporates intensification and negation, and is applied to the polarity classification task.
SENTIWORDNET: A Publicly Available Lexical Resource for Opinion Mining
2,489 Citations2006Andrea Esuli, Fabrizio Sebastiani
SENTIWORDNET is a lexical resource in which each WORDNET synset is associated to three numerical scores Obj, Pos and Neg, describing how objective, positive, and negative the terms contained in the synset are.
Journal of MarketingConsumer Evaluations of Brand Extensions
2,475 Citations1990David A. Aaker, Kevin Lane Keller
Machine LearningBoosTexter: A Boosting-based System for Text Categorization
2,194 Citations2000Robert E. Schapire, Yoram Singer
This work describes in detail an implementation, called BoosTexter, of the new boosting algorithms for text categorization tasks, and presents results comparing the performance of Boos Texter and a number of other text-categorization algorithms on a variety of tasks.
A holistic lexicon-based approach to opinion mining
1,388 Citations2008Xiaowen Ding, Bing Liu +1 more
This paper proposes a holistic lexicon-based approach to solving the problem of determining the semantic orientations (positive, negative or neutral) of opinions expressed on product features in reviews by exploiting external evidences and linguistic conventions of natural language expressions.
Journal of MarketingMarketing Universals: Consumers' Use of Brand Name, Price, Physical Appearance, and Retailer Reputation as Signals of Product Quality
1,083 Citations1994Niraj Dawar, Philip M. Parker
Proceedings of the 24th annual meeting on Association for Computational Linguistics
799 Citations1986Alan W. Biermann
This volume is the official record of the Twenty-Fourth Annual Meeting of the Association for Computational Linguistics and contains abstracts for the tutorials and panels as well as the texts of the presented papers.
Computational IntelligenceSENTIMENT CLASSIFICATION of MOVIE REVIEWS USING CONTEXTUAL VALENCE SHIFTERS
750 Citations2006Alistair Kennedy, Diana Inkpen
It is shown that extending the term‐counting method with contextual valence shifters improves the accuracy of the classification, and combining the two methods achieves better results than either method alone.
Computational LinguisticsRecognizing Contextual Polarity: An Exploration of Features for Phrase-Level Sentiment Analysis
731 Citations2009Theresa Wilson, Janyce Wiebe +1 more
The goal of this work is to automatically distinguish between prior and contextual polarity, with a focus on understanding which features are important for this task, and it is shown that the presence of neutral instances greatly degrades the performance of features for distinguishing between positive and negative polarity.
Communications of the ACMOvercoming the J-shaped distribution of product reviews
676 Citations2009Nan Hu, Jie Zhang +1 more
The existence of a J-shaped distribution is demonstrated, sources of bias that cause this distribution are identified, ways to overcome these biases are proposed, and it is shown that overcoming these biases helps product review systems better predict future product sales.
Automatically assessing review helpfulness
522 Citations2006Soo-Min Kim, Patrick Pantel +2 more
This paper considers the task of automatically assessing review helpfulness, and finds that the most useful features include the length of the review, its unigrams, and its product rating.
The information retrieval seriesContextual Valence Shifters
518 Citations2006Livia Polanyi, Annie Zaenen
It is argued that the current work in this area that concentrates mainly on the negative or positive attitude communicated by individual terms is incomplete and often gives the wrong results when implemented directly and proposes a simple, “proof of concept” implementation for some contextual shifters.
Topical N-Grams: Phrase and Topic Discovery, with an Application to Information Retrieval
486 Citations2007Xuerui Wang, Andrew McCallum +1 more
Low-Quality Product Review Detection in Opinion Summarization
392 Citations2007Jingjing Liu, Yunbo Cao +3 more
Experimental results show that the proposed approach effectively discriminates lowquality reviews from high-quality ones and enhances the task of opinion summarization by detecting and filtering low quality reviews.
Sentiment analysis of conditional sentences
242 Citations2009Ramanathan Narayanan, Bing Liu +1 more
This paper first presents a linguistic analysis of conditional sentences, and then builds some supervised learning models to determine if sentiments expressed on different topics in a conditional sentence are positive, negative or neutral.
Topic identification for fine-grained opinion analysis
192 Citations2008Veselin Stoyanov, Claire Cardie
This paper provides an operational definition of opinion topic and presents an algorithm for opinion topic identification that, following the new definition, treats the task as a problem in topic coreference resolution.
Voice of the customers: mining online customer reviews for product feature-based ranking
123 Citations2010Kunpeng Zhang, Ramanathan Narayanan +1 more
This paper presents a feature-based product ranking technique that mines thousands of customer reviews and model the relationships among products by constructing a weighted and directed graph to determine the relative quality of products.
PLoS ONEHealth-Related Hot Topic Detection in Online Communities Using Text Clustering
112 Citations2013Yingjie Lu, Pengzhu Zhang +3 more
Automatic topic detection based on document clustering is an alternative approach for extracting health-related hot topics in online communities and is integrated into medical domain-specific features to represent the messages posted in online health communities.
DSpace@MIT (Massachusetts Institute of Technology)Content Models with Attitude
76 Citations2011Christina Sauper, Aria Haghighi +1 more
A probabilistic topic model for jointly identifying properties and attributes of social media review snippets and captures aggregate user sentiments towards these properties that enables discovery of highly rated or inconsistent properties of a product.
Mining millions of reviews
68 Citations2011Kunpeng Zhang, Yu Cheng +2 more
A product ranking model that applies weights to product review factors to calculate a products ranking score is presented which produces product ranking results that closely relate to the products sales ranking as reported by the retailer.
SES: Sentiment Elicitation System for Social Media Data
56 Citations2011Kunpeng Zhang, Yu Cheng +7 more
A sentiment identification system called SES is developed which implements three different sentiment identification algorithms and augment basic compositional semantic rules in the first algorithm, and a machine learning model is employed on features derived from outputs of three algorithms.
Sentiment classification of customer reviews based on fuzzy logic
39 Citations2010Samaneh Nadali, Masrah Azrifah Azmi Murad +1 more
A fuzzy logic model is proposed to perform semantic classifications of customers review into the following sub-classes: very weak, weak, moderate, very strong and strong by combinations adjective, adverb and verb to increase holistic the accuracy of lexicon approach.
IEEE Internet ComputingRainbow Product Ranking for Upgrading E-Commerce
19 Citations2009Qinyuan Feng, Kai Hwang +1 more
The authors propose a rainbow ranking system that extends eBay's one-to-one shopping paradigm to a flexible one with many- to-many transactions and demonstrates a 50 to 70 percent transaction increase over skyline and eBay ranking methods.
Research of Product Ranking Technology Based on Opinion Mining
18 Citations2009Peiliang Tian, Yuanchao Liu +2 more
This paper focuses on mining opinion of Chinese review sentences, obtaining comprehensive evaluation of product and ranking product in some feature or in all features.
Automated Error Detection of Vocabulary Usage in College English Writing
3 Citations2010Shili Ge, Rou Song
Researchers’ examination finds that about 46% of the BAWPs in students’ compositions with the tagged frequency lower than 10 are language errors and close to 37% with the tags frequency higher than 30 are errors, which can greatly facilitate college English writing.