Linguistic characteristics of shill reviews
Electronic Commerce Research and ApplicationsPublished 23 October 2013
Toan C. Ong, Michael V. Mannino, Dawn G. Gregg
Citations57
SJR quartileQ1
SJR score1.41
SNIP1.70
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
Overall, the study provides improved understanding of shill reviews and demonstrates a method to extract and classify features from product reviews with an eventual goal to increase effectiveness of review filtering methods.
Abstract
This exploratory study investigates the linguistic characteristics of shill reviews and develops a tool for extracting product features from the text of product reviews. Shill reviews are increasingly used to manipulate the reputation of products sold on websites. To overcome limitations of identifying shill reviews, we collected shill reviews as primary data from students posing as shills. Using semi-automated natural language processing techniques, we compared shill reviews and normal reviews on informativeness, subjectivity and readability. The results showed evidence of substantial differences between shill reviews and normal reviews in both subjectivity and readability. Informativeness appears to be a mixed separator of shill and normal reviews so additional studies may be necessary. Overall, the study provides improved understanding of shill reviews and demonstrates a method to extract and classify features from product reviews with an eventual goal to increase effectiveness of review filtering methods.
Keywords
Computer ScienceSocial Sciences
The Quarterly Journal of EconomicsThe Market for "Lemons": Quality Uncertainty and the Market Mechanism
22,642 Citations1970George A. Akerlof
Foundations of statistical natural language processing
9,996 Citations1999Christopher D. Manning, Hinrich Schütze
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.
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.
Information Richness. A New Approach to Managerial Behavior and Organization Design
2,262 Citations1983Richard L. Daft, Robert H. Lengel
The concept of information richness is introduced, and three models of information processing are proposed that describe (1) manager information behavior, (2) organizational mechanisms for coping with equivocality from the environment, and (3) organizational mechanism for internal coordination.
Communications of the ACMReputation systems
2,153 Citations2000Paul Resnick, Ko Kuwabara +2 more
Systems T he Internet offers vast new opportunities to interact with total strangers, but these interactions can be fun, informative, even profitable, but they also involve risk.
The Journal of ReadingSMOG Grading - A New Readability Formula.
2,078 Citations1969G. Harry McLaughlin
Although this system, SMOG Grading, is laughably simple, it is in fact more valid than previous readability formulas and the rest of this paper is devoted to substantiating that claim.
Mining the peanut gallery
1,908 Citations2003Kushal Dave, Steve Lawrence +1 more
This work develops a method for automatically distinguishing between positive and negative reviews and draws on information retrieval techniques for feature extraction and scoring, and the results for various metrics and heuristics vary depending on the testing situation.
Extracting product features and opinions from reviews
1,720 Citations2005Ana-Maria Popescu, Oren Etzioni
Opine is introduced, an unsupervised information-extraction system which mines reviews in order to build a model of important product features, their evaluation by reviewers, and their relative quality across products.
Information Systems ResearchExamining the Relationship Between Reviews and Sales: The Role of Reviewer Identity Disclosure in Electronic Markets
1,640 Citations2008Chris Forman, Anindya Ghose +1 more
It is suggested that identity-relevant information about reviewers shapes community members' judgment of products and reviews and shows that shared geographical location increases the relationship between disclosure and product sales, thus highlighting the important role of geography in electronic commerce.
Opinion observer
1,604 Citations2005Bing Liu, Minqing Hu +1 more
A novel framework for analyzing and comparing consumer opinions of competing products is proposed, and a new technique based on language pattern mining is proposed to extract product features from Pros and Cons in a particular type of reviews.
Sentiment Analysis and Subjectivity
1,594 Citations2010Liu Bing
An intraocular lens for implantation in an eye comprising an optic configured so that the optic can be deformed to permit the intraocular Lens to be passed through an incision into the eye is provided.
Opinion spam and analysis
1,520 Citations2008Nitin Jindal, Bing Liu
It is shown that opinion spam is quite different from Web spam and email spam, and thus requires different detection techniques, and therefore requires some novel techniques to detect them.
Personality and Social Psychology BulletinLying Words: Predicting Deception from Linguistic Styles
1,457 Citations2003Matthew L. Newman, James W. Pennebaker +2 more
Information Processing & ManagementAn information-theoretic perspective of tf–idf measures
1,376 Citations2002Akiko Aizawa
The proposed PWI is expressed as a product of the occurrence probabilities of terms and their amounts of information, and corresponds well with the conventional term frequency-inverse document frequency measures that are commonly used in today's information retrieval systems.
Mining opinion features in customer reviews
1,273 Citations2004Minqing Hu, Bing Liu
This project aims to summarize all the customer reviews of a product by mining opinion/product features that the reviewers have commented on and a number of techniques are presented to mine such features.
International Journal of Hospitality ManagementThe impact of online user reviews on hotel room sales
1,260 Citations2008Qiang Ye, Rob Law +1 more
Handbook of Natural Language Processing
1,080 Citations2010Nitin Indurkhya, Fred J. Damerau
Fully updated with the latest developments in the field, this comprehensive, modern handbook emphasizes how to implement practical language processing tools in computational systems.
Management ScienceStrategic Manipulation of Internet Opinion Forums: Implications for Consumers and Firms
762 Citations2006Chrysanthos Dellarocas
Detecting product review spammers using rating behaviors
720 Citations2010Ee‐Peng Lim, Viet-An Nguyen +3 more
This paper identifies several characteristic behaviors of review spammers and model these behaviors so as to detect the spammers, and shows that the detected spammers have more significant impact on ratings compared with the unhelpful reviewers.
Shilling recommender systems for fun and profit
643 Citations2004Shyong K. Lam, John Riedl
Four open questions are explored that may affect the effectiveness of shilling attacks on recommender systems: which recommender algorithm is being used, whether the application is producing recommendations or predictions, how detectable the attacks are by the operator of the system, and what the properties are of the items being attacked.
Decision Support SystemsManipulation of online reviews: An analysis of ratings, readability, and sentiments
529 Citations2011Nan Hu, Indranil Bose +2 more
A simple statistical method is proposed to detect online reviews manipulation, and assess how consumers respond to products with manipulated reviews, and the effectiveness of manipulation through ratings, sentiments, and readability is investigated.
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.
Review spam detection
447 Citations2007Nitin Jindal, Bing Liu
This paper makes an attempt to study review spam and spam detection.
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.
Finding unusual review patterns using unexpected rules
339 Citations2010Nitin Jindal, Bing Liu +1 more
Using the technique, an Amazon.com review dataset is analyzed and many unexpected rules and rule groups which indicate spam activities are found.
Detecting Hoaxes, Frauds, and Deception in Writing Style Online
336 Citations2012Sadia Afroz, Michael Brennan +1 more
It is shown that using a large feature set, it is possible to distinguish regular documents from deceptive documents with 96.6% accuracy (F-measure) and an analysis of linguistic features that can be modified to hide writing style is presented.
Human Communication ResearchAN EXPLORATION OF DECEPTION AS A COMMUNICATION CONSTRUCT
328 Citations1974Mark L. Knapp, Roderick P. Hart +1 more
Methods in Ecology and EvolutionWhen should we use one‐tailed hypothesis testing?
263 Citations2010Graeme D. Ruxton, Markus Neuhäuser
It is suggested that authors should only use a one-tailed test if they can explain why they are more interested in an effect in one direction and not the other, and a further requirement that adoption of one-tails testing requires an explanation why the authors would treat a large observed difference in the unexpected direction no differently from a change in the expected direction.
Journal of Marketing ResearchExpectancy Theory Predictions of Salesmen's Performance
239 Citations1974Richard L. Oliver
Show me the money!
226 Citations2007Nikolay Archak, Anindya Ghose +1 more
A novel hybrid technique combining text mining and econometrics that models consumer product reviews as elements in a Tensor product of feature and evaluation spaces is developed and impute the quantitative impact of consumer reviews on product demand as a linear functional from this tensor product space.
Distortion as a validation criterion in the identification of suspicious reviews
159 Citations2010Guangyu Wu, Derek Greene +2 more
This paper proposes a distortion criterion for assessing the impact of methods for uncovering suspicious hotel reviews in TripAdvisor, and presents an evaluation of this strategy in the assessment of shill detection mechanisms on a dataset of hotel reviews collected from TripAdvisors.
Decision Support SystemsManipulation in digital word-of-mouth: A reality check for book reviews
137 Citations2010Nan Hu, Indranil Bose +2 more
It is revealed that fraudulent review manipulation is a serious problem for 1) non-bestseller books; 2) books whose reviews are classified as not very helpful; 3) books that experience greater variability in the helpfulness of their online reviews; and 4) popular books as well as high-priced books.
Is It the Review or the Reviewer? a Multi-Method Approach to Determine the Antecedents of Online Review Helpfulness
129 Citations2011Laura Connors, Susan M. Mudambi +1 more
One key finding is that reviews written by a self-described expert are more helpful than those that are not, which can provide guidance to online retailers and rating websites in their efforts to provide value to their customers.
SSRN Electronic JournalStrategic Manipulation of Internet Opinion Forums: Implications for Consumers and Firms
126 Citations2004Chrysanthos Dellarocas
A theoretical analysis of the impact of manipulation of online forums on firm profits and consumer surplus suggests that as the amount of user-contributed online content increases, it is firms, and not consumers, that have most to gain from the development of such technologies.
Decision Support SystemsThe roles of players and reputation: Evidence from eBay online auctions
112 Citations2006Jie Zhang
This paper explores the impact of the consumers' above behavior on the reputation system with an analytical model and empirical evidence from a popular online auction website eBay.
First MondaySix degrees of reputation: The use and abuse of online review and recommendation systems
106 Citations2006Shay David, Trevor Pinch
A framework for discussing the changes of the categories of authorship, creativity, expertise, and reputation that are being re–negotiated in this multi–tier reputation economy is suggested.
Lecture notes in computer scienceFeature and Opinion Mining for Customer Review Summarization
70 Citations2009Muhammad Abulaish, Jahiruddin +2 more
An opinion mining system to identify product features and opinions from review documents using semantic and linguistic analysis of text documents to present feature-based summary of review documents in a comprehendible way is presented.
Electronic Commerce Research and ApplicationsReputation inflation detection in a Chinese C2C market
38 Citations2011Weijia You, Lu Liu +2 more
A conceptual framework to identify the characteristics of collusive transactions based on the homo economicus assumption is presented and it is hypothesized that transaction-related indicators including price, frequency, comment, and connectedness to the transaction network, and individual- related indicators including reputation and age can be used to identify collusive traders.
Using readability tests to predict helpful product reviews
30 Citations2010Michael P. O’Mahony, Barry Smyth
The findings, based on a large-scale evaluation of TripAdvisor and Amazon reviews, indicate that structural and readability features are useful predictors for Amazon product reviews but less so for TripAdvisors hotel reviews.
Online Reviews as a Driver of New Product Sales
29 Citations2010Geng Cui, Hon‐Kwong Lui +1 more
Analyses of panel data of 332 new products from Amazon.com indicate that negative reviews affect new product sales more than positive reviews, but also in a positive way, suggesting a significant cascade effect.
Journal of the Association for Information SystemsWhat Does That Mean? Investigating Obfuscation and Readability Cues as Indicators of Deception in Fraudulent Financial Reports
26 Citations2009Kevin Moffitt, Mary B. Burns
These findings suggest that authors of fraudulent 10-Ks chose more complex words, signaling words of achievement and cause, and qualifying conjunctions, as well as more present tense verbs and were easier to read as indicated by the FRE readability measure.
“I Don’t Know Where He is Notâ€: Does Deception Research yet Offer a Basis for Deception Detectives?
13 Citations2012Anna Vartapetiance, Lee Gillam
SSRN Electronic JournalEvaluating Content Quality and Usefulness of Online Product Reviews
5 Citations2008Nikolaos Korfiatis
The results of these evaluations indicate that the usefulness score of a particular review is significantly affected by the qualitative characteristics of the review as measured by readability tests applied to a large dataset of reviews collected from the United Kingdom section of the popular online marketplace Amazon.
Dépôt institutionnel de l'Université libre de Bruxelles (Université Libre de Bruxelles)A stuttering child with linguistic difficulties: A case study
1 Citations1991Henny Bijleveld