Processing

Please wait...

Settings

Settings

Goto Application

1. WO2021041830 - SYSTEM AND METHOD FOR MACHINE LEARNING BASED PREDICTION OF SOCIAL MEDIA INFLUENCE OPERATIONS

Publication Number WO/2021/041830
Publication Date 04.03.2021
International Application No. PCT/US2020/048436
International Filing Date 28.08.2020
Chapter 2 Demand Filed 22.01.2021
IPC
G06N 20/00 2019.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
G06N 5/04 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
5Computer systems using knowledge-based models
04Inference methods or devices
G06N 99/00 2019.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
99Subject matter not provided for in other groups of this subclass
G06Q 30/02 2012.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
30Commerce, e.g. shopping or e-commerce
02Marketing, e.g. market research and analysis, surveying, promotions, advertising, buyer profiling, customer management or rewards; Price estimation or determination
CPC
G06N 20/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
G06N 5/04
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
5Computer systems using knowledge-based models
04Inference methods or devices
G06N 99/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
99Subject matter not provided for in other groups of this subclass
G06Q 30/0242
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
30Commerce, e.g. shopping or e-commerce
02Marketing, e.g. market research and analysis, surveying, promotions, advertising, buyer profiling, customer management or rewards; Price estimation or determination
0241Advertisement
0242Determination of advertisement effectiveness
G06Q 50/01
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
50Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
01Social networking
Applicants
  • THE TRUSTEES OF PRINCETON UNIVERSITY [US]/[US]
Inventors
  • ALIZADEH, Meysam
  • SHAPIRO, Jacob
Agents
  • DRACHTMAN, Craig, M.
Priority Data
62/893,00528.08.2019US
62/992,55120.03.2020US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) SYSTEM AND METHOD FOR MACHINE LEARNING BASED PREDICTION OF SOCIAL MEDIA INFLUENCE OPERATIONS
(FR) SYSTÈME ET PROCÉDÉ DE PRÉDICTION D'OPÉRATIONS D'INFLUENCE DE RÉSEAUX SOCIAUX BASÉE SUR L'APPRENTISSAGE AUTOMATIQUE
Abstract
(EN)
According to various embodiments, a machine learning based method, system, and non- transitory computer-readable medium for identifying content on social media related to one or more coordinated influence efforts are disclosed. The method includes generating one or more datasets of post-uniform resource locator (URL) pairs produced from one or more known coordinated influence efforts on one or more social media platforms. The method further includes generating one or more datasets of post-URL pairs produced from one or more random users on one or more social media platforms. The method additionally includes extracting a plurality of content-based features from the post-URL pairs from known coordinated influence efforts and random users. The method also includes iteratively training a classifier over a predetermined period of time to distinguish between a post-URL pair produced from a coordinated influence effort and a post-URL pair produced from a random user using the extracted plurality of content-based features.
(FR)
Selon divers modes de réalisation, l'invention concerne un procédé, un système et un support non transitoire lisible par ordinateur basés sur l'apprentissage automatique qui permettent d'identifier du contenu sur des réseaux sociaux lié à un ou plusieurs efforts d'influence coordonnés. Le procédé consiste à générer un ou plusieurs ensembles de données de paires de post-URL produites à partir d'un ou de plusieurs efforts d'influence coordonnés connus sur une ou plusieurs plateformes de réseaux sociaux. Le procédé consiste en outre à générer un ou plusieurs ensembles de données de paires de post-URL produites à partir d'un ou de plusieurs utilisateurs aléatoires sur une ou plusieurs plateformes de réseaux sociaux. Le procédé consiste en outre à extraire une pluralité de caractéristiques basées sur du contenu à partir des paires de post-URL à partir d'efforts d'influence coordonnés connus et d'utilisateurs aléatoires. Le procédé comprend également l'entraînement itératif d'un classificateur sur une période prédéfinie pour faire la distinction entre une paire de post-URL produite à partir d'un effort d'influence coordonnée et une paire de post-URL produite à partir d'un utilisateur aléatoire à l'aide de la pluralité de caractéristiques basées sur du contenu extraite.
Latest bibliographic data on file with the International Bureau