Identifying fake review systems to protect consumers from fraudulent e-commerce websites
Systems and methods for detecting fraudulent e-commerce websites by identifying fake review systems are disclosed. In particular, some embodiments may identify an e-commerce website and download content contained on one or more product web pages of the e-commerce website. These web pages may be analyzed to identify a product review feature that is within the one or more product web pages. Attributes of the product review feature may then be evaluated to determine that the e-commerce website is fraudulent and a security action may be performed to protect consumers from the e-commerce website.
1 . A computer-implemented method for detecting fraudulent e-commerce websites, at least a portion of the method being performed by a computing device comprising one or more processors, the method comprising:
identifying an e-commerce website;
downloading content contained on one or more product web pages of the e-commerce website;
identifying a product review feature contained within the one or more product web pages;
determining whether the product review feature is a first-party review system or a third-party review system;
evaluating attributes associated with the product review feature to determine that the e-commerce website is fraudulent, wherein at least one of the evaluated attributes are evaluated based on whether the product review feature is a first-party review system or a third-party review system; and
performing a security action, via a user device, based on the determination that the e-commerce website is fraudulent, the security action including at least one of:
providing a notification on the user device indicating that the e-commerce website may be fraudulent;
preventing access to the e-commerce website; or
preventing purchases from the e-commerce website.
2 . The method of claim 1 , wherein the content downloaded contained on one or more product web pages includes images and hypertext markup language (HTML) code.
3 . The method of claim 1 , wherein the content contained on the one or more product web pages of the e-commerce website is downloaded by crawling and indexing the content contained on the one or more product web pages.
4 . The method of claim 3 , wherein a headless browser is used to crawl the e-commerce website.
5 . The method of claim 1 , wherein the product review feature is identified through one or more visual cues.
6 . The method of claim 5 , wherein the visual cues include a logo of a third-party review platform or a customer review box or a rating scale visual.
7 . The method of claim 6 , wherein the ratings scale visual includes one or more stars.
8 . The method of claim 1 , wherein:
the product review feature is determined be the third-party review system,
the attributes evaluated include an integration with a third-party review platform, and
the e-commerce website is determined to be fraudulent when an integration with the third-party review platform is nonfunctional.
9 . The method of claim 8 , wherein the integration with the third-party review platform is nonfunctional when a request is not made to the third-party review system or when a requested uniform resource locator (URL) lacks a domain of the e-commerce website.
10 . The method of claim 1 , wherein:
the product review feature is determined to be the first-party review system,
the attributes evaluated include a functionality of a review submission feature, and
the e-commerce website is determined to be fraudulent when the review submission feature is inoperable.
11 . The method of claim 10 , wherein the review submission feature lacks a review submission link.
12 . The method of claim 1 , wherein:
the product review feature includes a plurality of reviews,
the attributes evaluated include a ratio of high rated reviews to low rated reviews, and
the e-commerce website is determined to be fraudulent when the ratio of high rated reviews to low rated reviews exceeds a threshold.
13 . The method of claim 1 , wherein:
the product review feature includes a plurality of reviews,
the attributes evaluated include an average length of the plurality of reviews, and
the e-commerce website is determined to be fraudulent when the average length of the plurality of reviews falls below a threshold.
14 . The method of claim 1 , wherein:
the product review feature includes a plurality of reviews,
the attributes evaluated include a level of similarity of the plurality of reviews, and
the e-commerce website is determined to be fraudulent when the level of similarity of the plurality of reviews exceeds a threshold.
15 . The method of claim 1 , wherein:
the product review feature includes a plurality of reviews,
the attributes evaluated include a level of grammatical accuracy of the plurality of reviews, and
the e-commerce website is determined to be fraudulent when the level of grammatical accuracy of the plurality of reviews falls below a threshold.
16 . The method of claim 1 , wherein the security action includes providing a notification on the user device that the e-commerce website may be fraudulent.
17 . The method of claim 1 , wherein the security action includes preventing access to the e-commerce website.
18 . The method of claim 1 , wherein the security action includes preventing purchases from the e-commerce website.
19 . One or more non-transitory computer-readable media comprising one or more computer-readable instructions that, when executed by one or more processors of a computing device, cause the computing device to perform a method for detecting fraudulent e-commerce websites, the method comprising:
identifying an e-commerce website;
downloading content contained on one or more product web pages of the e-commerce website;
identifying a product review feature contained within the one or more product web pages;
determining whether the product review feature is a first-party review system or a third-party review system;
evaluating attributes associated with the product review feature to determine that the e-commerce website is fraudulent, wherein at least one of the evaluated attributes are evaluated based on whether the product review feature is a first-party review system or a third-party review system; and
performing a security action, via a user device, based on the determination that the e-commerce website is fraudulent, the security action including at least one of:
providing a notification on the user device indicating that the e-commerce website may be fraudulent;
preventing access to the e-commerce website; or
preventing purchases from the e-commerce website.
20 . A computing device comprising:
one or more processors; and
one or more non-transitory computer-readable media comprising one or more computer-readable instructions that, when executed by the one or more processors, cause the computing device to perform a method for detecting fraudulent e-commerce websites, the method comprising:
identifying an e-commerce website;
downloading content contained on one or more product web pages of the e-commerce website;
identifying a product review feature contained within the one or more product web pages;
determining whether the product review feature is a first-party review system or a third-party review system;
evaluating attributes associated with the product review feature to determine that the e-commerce website is fraudulent, wherein at least one of the evaluated attributes are evaluated based on whether the product review feature is a first-party review system or a third-party review system; and
performing a security action, via a user device, based on the determination that the e-commerce website is fraudulent, the security action including at least one of:
providing a notification on the user device indicating that the e-commerce website may be fraudulent;
preventing access to the e-commerce website; or
preventing purchases from the e-commerce website.