Google has been granted a patent by the USPTO to stop people from impersonating others on the web. This phenomenon has grown very quickly over the years, especially on social networking sites such as Twitter.
Google’s Patent Background:
A social network can be an online system that provides a forum for geographically separated users to interact with one another. Social networks can be aimed at different types of social interaction, such as friendship and business networking. A user of a social network can have a profile page (e.g., a web page on the social network) that provides information about the user to other users of the social network. A profile can include information regarding a user’s acquaintance relationships (e.g., friends, colleagues, schoolmates, etc.) on the social network.
A user can impersonate (e.g., assume the identity of another) another user on a social network by creating a profile page that contains content identifying the impersonated user (e.g., the victim of impersonation). For example, a first user can impersonate a second user on a social network by creating a profile page that contains identifying information about the second user, such as the second user’s name, age, location, occupation, and photograph. An impersonating profile page may copy some or all of the impersonating content from the victim’s profile page. Impersonation may be performed for a variety of reasons, such as malice toward the victim (e.g., impersonator has intent to defame the victim), and/or intent to usurp the victim’s influence on a social network (e.g., impersonator able to garner the victim’s reputation when recommending a product to the victim’s friends).
Detecting impersonation on a social network has included manual review of an alleged impersonator’s profile page and, in some cases, review of an alleged victim’s profile page by a human.
This document describes techniques, methods, systems, and mechanisms for detecting impersonation of a user’s profile page on a social network. In general, impersonation can be detected by comparing elements (e.g., fields, photos, metadata, etc.) of a profile page of an alleged impersonator with elements of a profile page of an alleged victim. Such a comparison can yield signals indicating that the profile page of the alleged impersonator is likely impersonating the profile page of the alleged victim. Based upon detected signals indicating impersonation, a determination can be made as to a likelihood that the profile page of the alleged impersonator is impersonating the profile page of the alleged victim.
In one implementation, a computer-implemented method includes receiving at a server system a claim that identifies a first user profile page on a social network as allegedly impersonating a second user profile page on the social network, and retrieving by the server system first information associated with the first user profile page and second information associated with the second user profile page. The method can also include comparing by the server system the first information and the second information to identify indicators of impersonation, wherein comparing the first information and the second information to identify indicators of impersonation comprises identifying similarities of elements on the first user profile page and corresponding elements on the second user profile page. The method can further include, based upon the identified indicators of impersonation, determining that the first user profile page is likely impersonating the second user profile page on the social network, wherein first user profile page is determined to be likely impersonating the second user profile page when the first and second user profile pages are determined to be similar to each other; and returning by the server system a flag indicating that the first user profile page is likely impersonating the second user profile page. Read more…