@inproceedings{daryani-caverlee-2021-identifying,
title = "Identifying Hijacked Reviews",
author = "Daryani, Monika and
Caverlee, James",
editor = "Malmasi, Shervin and
Kallumadi, Surya and
Ueffing, Nicola and
Rokhlenko, Oleg and
Agichtein, Eugene and
Guy, Ido",
booktitle = "Proceedings of the 4th Workshop on e-Commerce and NLP",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.ecnlp-1.9",
doi = "10.18653/v1/2021.ecnlp-1.9",
pages = "70--78",
abstract = "Fake reviews and review manipulation are growing problems on online marketplaces globally. Review Hijacking is a new review manipulation tactic in which unethical sellers {``}hijack{''} an existing product page (usually one with many positive reviews), then update the product details like title, photo, and description with those of an entirely different product. With the earlier reviews still attached, the new item appears well-reviewed. So far, little knowledge about hijacked reviews has resulted in little academic research and an absence of labeled data. Hence, this paper proposes a three-part study: (i) we propose a framework to generate synthetically labeled data for review hijacking by swapping products and reviews; (ii) then, we evaluate the potential of both a Siamese LSTM network and BERT sequence pair classifier to distinguish legitimate reviews from hijacked ones using this data; and (iii) we then deploy the best performing model on a collection of 31K products (with 6.5 M reviews) in the original data, where we find 100s of previously unknown examples of review hijacking.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="daryani-caverlee-2021-identifying">
<titleInfo>
<title>Identifying Hijacked Reviews</title>
</titleInfo>
<name type="personal">
<namePart type="given">Monika</namePart>
<namePart type="family">Daryani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Caverlee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on e-Commerce and NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shervin</namePart>
<namePart type="family">Malmasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Surya</namePart>
<namePart type="family">Kallumadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicola</namePart>
<namePart type="family">Ueffing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oleg</namePart>
<namePart type="family">Rokhlenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugene</namePart>
<namePart type="family">Agichtein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ido</namePart>
<namePart type="family">Guy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Fake reviews and review manipulation are growing problems on online marketplaces globally. Review Hijacking is a new review manipulation tactic in which unethical sellers “hijack” an existing product page (usually one with many positive reviews), then update the product details like title, photo, and description with those of an entirely different product. With the earlier reviews still attached, the new item appears well-reviewed. So far, little knowledge about hijacked reviews has resulted in little academic research and an absence of labeled data. Hence, this paper proposes a three-part study: (i) we propose a framework to generate synthetically labeled data for review hijacking by swapping products and reviews; (ii) then, we evaluate the potential of both a Siamese LSTM network and BERT sequence pair classifier to distinguish legitimate reviews from hijacked ones using this data; and (iii) we then deploy the best performing model on a collection of 31K products (with 6.5 M reviews) in the original data, where we find 100s of previously unknown examples of review hijacking.</abstract>
<identifier type="citekey">daryani-caverlee-2021-identifying</identifier>
<identifier type="doi">10.18653/v1/2021.ecnlp-1.9</identifier>
<location>
<url>https://aclanthology.org/2021.ecnlp-1.9</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>70</start>
<end>78</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Identifying Hijacked Reviews
%A Daryani, Monika
%A Caverlee, James
%Y Malmasi, Shervin
%Y Kallumadi, Surya
%Y Ueffing, Nicola
%Y Rokhlenko, Oleg
%Y Agichtein, Eugene
%Y Guy, Ido
%S Proceedings of the 4th Workshop on e-Commerce and NLP
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F daryani-caverlee-2021-identifying
%X Fake reviews and review manipulation are growing problems on online marketplaces globally. Review Hijacking is a new review manipulation tactic in which unethical sellers “hijack” an existing product page (usually one with many positive reviews), then update the product details like title, photo, and description with those of an entirely different product. With the earlier reviews still attached, the new item appears well-reviewed. So far, little knowledge about hijacked reviews has resulted in little academic research and an absence of labeled data. Hence, this paper proposes a three-part study: (i) we propose a framework to generate synthetically labeled data for review hijacking by swapping products and reviews; (ii) then, we evaluate the potential of both a Siamese LSTM network and BERT sequence pair classifier to distinguish legitimate reviews from hijacked ones using this data; and (iii) we then deploy the best performing model on a collection of 31K products (with 6.5 M reviews) in the original data, where we find 100s of previously unknown examples of review hijacking.
%R 10.18653/v1/2021.ecnlp-1.9
%U https://aclanthology.org/2021.ecnlp-1.9
%U https://doi.org/10.18653/v1/2021.ecnlp-1.9
%P 70-78
Markdown (Informal)
[Identifying Hijacked Reviews](https://aclanthology.org/2021.ecnlp-1.9) (Daryani & Caverlee, ECNLP 2021)
ACL
- Monika Daryani and James Caverlee. 2021. Identifying Hijacked Reviews. In Proceedings of the 4th Workshop on e-Commerce and NLP, pages 70–78, Online. Association for Computational Linguistics.