Stevens Institute of Technology - The Innovation University®
UndergraduateGraduate
Give NowLearn about GivingThe Power of Stevens Campaign
Future Student​​Parents and Family MembersStevens Alumnus/a​High School Counselor​Corporate Partner​Current Student​Friend of Stevens Log in to mySTEVENS

Search form

VisitVirtual TourAlumniNewsDirectoryAthleticsmyStevens
    About Stevens
    MissionStevens HistoryFacts & StatisticsRankings and RecognitionLeadershipStrategic PlanSustainabilityCommunity EngagementUniversity Policy LibraryAccreditationConsumer Information
    Admissions
    Undergraduate AdmissionsGraduate AdmissionsStevens Veterans OfficePre-College ProgramsTuition & Financial AidSuccess After Stevens
    Academics
    Undergraduate StudiesGraduate StudiesColleges & SchoolsStevens OnlineAcademic CatalogTechnology & Entrepreneurial ThinkingContinuing and Professional EducationGlobal OpportunitiesAcademic CultureLibrary
    Research & Entrepreneurship
    Foundational Research PillarsAnnual Innovation ExpoFaculty ResearchStudent ResearchInnovation & EntrepreneurshipStevens Venture CenterSolar DecathlonPartner with Stevens
    Campus Life
    Living at Stevens Student Affairs Undergrad Student LifeGraduate Student AffairsCareer Center Health & WellnessDiversity and Inclusion​AthleticsArts on Campus​Life in Hoboken Commencement

Available Patents & Technologies

HomeDirectory Office of Innovation and EntrepreneurshipAvailable Patents & Technologies

Search for Technologies

All Technologies  - Advanced Search   - Algolia Search  

Case ID:
FY15-018

Method and Apparatus to Identify the Source of Information/Misinformation in Large-scale Social Media Networks

Case ID:
FY15-018
Web Published:
7/30/2018
Description:

Background:

Social media networks have experienced a meteoric rise in popularity. Information spread much faster in social networks than any other communication method as of this writing. This ease of information dissemination can be a double-edged sword, however, as social networks can also be used to spread rumors or computer malware. In such circumstances, detecting and determining the source of rumors or misinformation in a social network becomes valuable as a part of an affected party's damage control.

One potential source of information/misinformation may be a result of a node with a high degree of centrality (e.g., a node with a large number of friends on Facebook). This, however, is unlikely, because, in general, every node in a social network has the potential to spread information/misinformation.

It may be possible to use information from a snapshot of infected nodes to identify the source of information/misinformation. This requires the assumption that all nodes in the network monitor and report their status, which is not practical in large-scale social networks. Furthermore, this assumes that the underlying social graph is a regular tree. In general, however, an underlying social graph can be any type of graph.

It may also be possible to use a subset of nodes (called sensors) in the social network to find the source of information/misinformation. The foregoing methods require a large number of nodes in the network to act as sensors which is generally impractical. Furthermore, these methods do not consider the varying inter-node relationship strengths.

Summary:

In view of the foregoing background, a system and method of detecting a source of a rumor in a social media network is disclosed. The system and method involves identifying a plurality of node clusters in the network, each of the plurality of node clusters including a plurality of nodes, each of the plurality of nodes from each of the plurality of node clusters having at least one edge connection defined by a connection to a different node from a same one of the node clusters; identifying a plurality of gateway nodes from each of the plurality of node clusters, each gateway node from each of the plurality of node clusters as having at least one weak tie connection with a corresponding gateway node from a different one of the plurality of node clusters; selecting a subset of the plurality of gateway nodes as sensor nodes; measuring arrival times of the information from a source node at each of the sensor nodes; selecting a candidate node cluster from the plurality of node clusters based on high betweenness centrality, the candidate node cluster having a high probability of including the source node from among its corresponding plurality of nodes; selecting a subset of the plurality of nodes in the candidate cluster as candidate sensor nodes; measuring arrival times of the information from a source node at each of the candidate sensor nodes; and selecting a candidate node from the candidate cluster based on high betweenness centrality, the candidate node having a high probability of being the source node.

 

Patent Information:
Title App Type Country Serial No. Patent No. File Date Issued Date Expire Date
Direct Link:
https://stevens.testtechnologypublisher.com/technology/11236
FY15-018
Category(s):
Information Assurance/Cyber Security
Bookmark this page
Download as PDF
For Information, Contact:
David Zimmerman
Director of Technology Commercialization
Stevens Institute of Technogology
dzimmer3@stevens.edu
Inventors:
  • Alireza Louni
  • Koduvayur Subbalakshmi
Keywords:

A premier, private research university just minutes from New York City with an incredible view and exceptional access to opportunity

© 2018 Stevens Institute of Technology.
All Rights Reserved.
Privacy Policy | Emergency Info

myStevens BookstoreMake a GiftEventsCareers
Our Location

A premier, private research university just minutes from New York City with an incredible view and exceptional access to opportunity

Stevens Institute of Technology

1 Castle Point Terrace
Hoboken, NJ 07030

Get in Touch
201.216.5000
Social Media
FacebookTwitterInstagramYouTubeLinkedInSocial Media Hub