×

Method and apparatus to identify outliers in social networks

  • US 9,965,563 B2
  • Filed: 05/08/2017
  • Issued: 05/08/2018
  • Est. Priority Date: 09/29/2009
  • Status: Active Grant
First Claim
Patent Images

1. A method, comprising:

  • reducing, by a processing system including a processor, a sampling size of a population of social network users of an on-line social network based on a comparison of seed information to the population of social network users to obtain a reduced population of social network users of the on-line social network;

    sampling, by the processing system, the population of social network users to obtain first sampled social network users;

    sampling, by the processing system, the reduced population of social network users utilizing a crawl algorithm to obtain second sampled social network users;

    generating, by the processing system, a social network graph based on the first sampled social network users and the second sampled social network users, wherein the social network graph comprises an arrangement of the first sampled social network users and the second sampled social network users based on relationships between members of the first sampled social network users and the second sampled social network users arising in the on-line social network;

    characterizing, by the processing system, a cluster of social network users within the reduced population of social network users; and

    identifying, by the processing system, an outlier in the reduced population of social network users based on the characterizing of the cluster of social network users, wherein the outlier does not conform to the social network graph, wherein the second sampled social network users comprise current users and users being followed by the current users, wherein the second sampled social network users comprise inactive users of the on-line social network, wherein obtaining the seed information comprises receiving from a third party the seed information, wherein the method further comprises receiving, by the processing system, the social network graph, and wherein the first sampled social network users comprise a substantially random sample of the population of social network users, and wherein the identifying of the outlier is based on an intra-graph property of the social network graph.

View all claims
  • 1 Assignment
Timeline View
Assignment View
    ×
    ×