Inferring Users’ Social Roles with a Multi-Level Graph Neural Network Model

Users of social networks have a variety of social statuses and roles. For example, the users of Weibo include celebrities, government officials, and social organizations. At the same time, these users may be senior managers, middle managers, or workers in companies. Previous studies on this topic ha...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Chunrui Zhang, Shen Wang, Dechen Zhan, Mingyong Yin, Fang Lou
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	network representation learning graph neural networks social networks social status and role inference Science Q Astrophysics QB460-466 Physics QC1-999
Acceso en línea:	https://doaj.org/article/90685565036946a591462091f5e0ff22
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:90685565036946a591462091f5e0ff22
record_format	dspace
spelling	oai:doaj.org-article:90685565036946a591462091f5e0ff222021-11-25T17:29:47ZInferring Users’ Social Roles with a Multi-Level Graph Neural Network Model10.3390/e231114531099-4300https://doaj.org/article/90685565036946a591462091f5e0ff222021-11-01T00:00:00Zhttps://www.mdpi.com/1099-4300/23/11/1453https://doaj.org/toc/1099-4300Users of social networks have a variety of social statuses and roles. For example, the users of Weibo include celebrities, government officials, and social organizations. At the same time, these users may be senior managers, middle managers, or workers in companies. Previous studies on this topic have mainly focused on using the categorical, textual and topological data of a social network to predict users’ social statuses and roles. However, this cannot fully reflect the overall characteristics of users’ social statuses and roles in a social network. In this paper, we consider what social network structures reflect users’ social statuses and roles since social networks are designed to connect people. Taking an Enron email dataset as an example, we analyzed a preprocessing mechanism used for social network datasets that can extract users’ dynamic behavior features. We further designed a novel social network representation learning algorithm in order to infer users’ social statuses and roles in social networks through the use of an attention and gate mechanism on users’ neighbors. The extensive experimental results gained from four publicly available datasets indicate that our solution achieves an average accuracy improvement of 2% compared with GraphSAGE-Mean, which is the best applicable inductive representation learning method.Chunrui ZhangShen WangDechen ZhanMingyong YinFang LouMDPI AGarticlenetwork representation learninggraph neural networkssocial networkssocial status and role inferenceScienceQAstrophysicsQB460-466PhysicsQC1-999ENEntropy, Vol 23, Iss 1453, p 1453 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	network representation learning graph neural networks social networks social status and role inference Science Q Astrophysics QB460-466 Physics QC1-999
spellingShingle	network representation learning graph neural networks social networks social status and role inference Science Q Astrophysics QB460-466 Physics QC1-999 Chunrui Zhang Shen Wang Dechen Zhan Mingyong Yin Fang Lou Inferring Users’ Social Roles with a Multi-Level Graph Neural Network Model
description	Users of social networks have a variety of social statuses and roles. For example, the users of Weibo include celebrities, government officials, and social organizations. At the same time, these users may be senior managers, middle managers, or workers in companies. Previous studies on this topic have mainly focused on using the categorical, textual and topological data of a social network to predict users’ social statuses and roles. However, this cannot fully reflect the overall characteristics of users’ social statuses and roles in a social network. In this paper, we consider what social network structures reflect users’ social statuses and roles since social networks are designed to connect people. Taking an Enron email dataset as an example, we analyzed a preprocessing mechanism used for social network datasets that can extract users’ dynamic behavior features. We further designed a novel social network representation learning algorithm in order to infer users’ social statuses and roles in social networks through the use of an attention and gate mechanism on users’ neighbors. The extensive experimental results gained from four publicly available datasets indicate that our solution achieves an average accuracy improvement of 2% compared with GraphSAGE-Mean, which is the best applicable inductive representation learning method.
format	article
author	Chunrui Zhang Shen Wang Dechen Zhan Mingyong Yin Fang Lou
author_facet	Chunrui Zhang Shen Wang Dechen Zhan Mingyong Yin Fang Lou
author_sort	Chunrui Zhang
title	Inferring Users’ Social Roles with a Multi-Level Graph Neural Network Model
title_short	Inferring Users’ Social Roles with a Multi-Level Graph Neural Network Model
title_full	Inferring Users’ Social Roles with a Multi-Level Graph Neural Network Model
title_fullStr	Inferring Users’ Social Roles with a Multi-Level Graph Neural Network Model
title_full_unstemmed	Inferring Users’ Social Roles with a Multi-Level Graph Neural Network Model
title_sort	inferring users’ social roles with a multi-level graph neural network model
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/90685565036946a591462091f5e0ff22
work_keys_str_mv	AT chunruizhang inferringuserssocialroleswithamultilevelgraphneuralnetworkmodel AT shenwang inferringuserssocialroleswithamultilevelgraphneuralnetworkmodel AT dechenzhan inferringuserssocialroleswithamultilevelgraphneuralnetworkmodel AT mingyongyin inferringuserssocialroleswithamultilevelgraphneuralnetworkmodel AT fanglou inferringuserssocialroleswithamultilevelgraphneuralnetworkmodel
_version_	1718412298003939328

Inferring Users’ Social Roles with a Multi-Level Graph Neural Network Model

Ejemplares similares