Creating and detecting fake reviews of online products

<p>Customers increasingly rely on reviews for product information. However, the usefulness of online reviews is impeded by fake reviews that give an untruthful picture of product quality. Therefore, detection of fake reviews is needed. Unfortunately, so far, automatic detection has only had pa...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Joni Salminen (7434770) (author)
مؤلفون آخرون: Chandrashekhar Kandpal (19517671) (author), Ahmed Mohamed Kamel (19517674) (author), Soon-gyo Jung (7434773) (author), Bernard J. Jansen (7434779) (author)
منشور في: 2022
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513506168012800
author Joni Salminen (7434770)
author2 Chandrashekhar Kandpal (19517671)
Ahmed Mohamed Kamel (19517674)
Soon-gyo Jung (7434773)
Bernard J. Jansen (7434779)
author2_role author
author
author
author
author_facet Joni Salminen (7434770)
Chandrashekhar Kandpal (19517671)
Ahmed Mohamed Kamel (19517674)
Soon-gyo Jung (7434773)
Bernard J. Jansen (7434779)
author_role author
dc.creator.none.fl_str_mv Joni Salminen (7434770)
Chandrashekhar Kandpal (19517671)
Ahmed Mohamed Kamel (19517674)
Soon-gyo Jung (7434773)
Bernard J. Jansen (7434779)
dc.date.none.fl_str_mv 2022-09-20T12:00:00Z
dc.identifier.none.fl_str_mv 10.1016/j.jretconser.2021.102771
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Creating_and_detecting_fake_reviews_of_online_products/26889430
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Artificial intelligence
Data management and data science
Machine learning
Fake reviews
Detectione-commercee
WOM
Marketing
dc.title.none.fl_str_mv Creating and detecting fake reviews of online products
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p>Customers increasingly rely on reviews for product information. However, the usefulness of online reviews is impeded by fake reviews that give an untruthful picture of product quality. Therefore, detection of fake reviews is needed. Unfortunately, so far, automatic detection has only had partial success in this challenging task. In this research, we address the creation and detection of fake reviews. First, we experiment with two language models, ULMFiT and GPT-2, to generate fake product reviews based on an Amazon e-commerce dataset. Using the better model, GPT-2, we create a dataset for a classification task of fake review detection. We show that a machine classifier can accomplish this goal near-perfectly, whereas human raters exhibit significantly lower accuracy and agreement than the tested algorithms. The model was also effective on detected human generated fake reviews. The results imply that, while fake review detection is challenging for humans, “machines can fight machines” in the task of detecting fake reviews. Our findings have implications for consumer protection, defense of firms from unfair competition, and responsibility of review platforms.</p><h2>Other Information</h2> <p> Published in: Journal of Retailing and Consumer Services<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.jretconser.2021.102771" target="_blank">https://dx.doi.org/10.1016/j.jretconser.2021.102771</a></p>
eu_rights_str_mv openAccess
id Manara2_50c77dbd7a525facbf6fe5fbfc66f25d
identifier_str_mv 10.1016/j.jretconser.2021.102771
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/26889430
publishDate 2022
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Creating and detecting fake reviews of online productsJoni Salminen (7434770)Chandrashekhar Kandpal (19517671)Ahmed Mohamed Kamel (19517674)Soon-gyo Jung (7434773)Bernard J. Jansen (7434779)Information and computing sciencesArtificial intelligenceData management and data scienceMachine learningFake reviewsDetectione-commerceeWOMMarketing<p>Customers increasingly rely on reviews for product information. However, the usefulness of online reviews is impeded by fake reviews that give an untruthful picture of product quality. Therefore, detection of fake reviews is needed. Unfortunately, so far, automatic detection has only had partial success in this challenging task. In this research, we address the creation and detection of fake reviews. First, we experiment with two language models, ULMFiT and GPT-2, to generate fake product reviews based on an Amazon e-commerce dataset. Using the better model, GPT-2, we create a dataset for a classification task of fake review detection. We show that a machine classifier can accomplish this goal near-perfectly, whereas human raters exhibit significantly lower accuracy and agreement than the tested algorithms. The model was also effective on detected human generated fake reviews. The results imply that, while fake review detection is challenging for humans, “machines can fight machines” in the task of detecting fake reviews. Our findings have implications for consumer protection, defense of firms from unfair competition, and responsibility of review platforms.</p><h2>Other Information</h2> <p> Published in: Journal of Retailing and Consumer Services<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.jretconser.2021.102771" target="_blank">https://dx.doi.org/10.1016/j.jretconser.2021.102771</a></p>2022-09-20T12:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1016/j.jretconser.2021.102771https://figshare.com/articles/journal_contribution/Creating_and_detecting_fake_reviews_of_online_products/26889430CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/268894302022-09-20T12:00:00Z
spellingShingle Creating and detecting fake reviews of online products
Joni Salminen (7434770)
Information and computing sciences
Artificial intelligence
Data management and data science
Machine learning
Fake reviews
Detectione-commercee
WOM
Marketing
status_str publishedVersion
title Creating and detecting fake reviews of online products
title_full Creating and detecting fake reviews of online products
title_fullStr Creating and detecting fake reviews of online products
title_full_unstemmed Creating and detecting fake reviews of online products
title_short Creating and detecting fake reviews of online products
title_sort Creating and detecting fake reviews of online products
topic Information and computing sciences
Artificial intelligence
Data management and data science
Machine learning
Fake reviews
Detectione-commercee
WOM
Marketing