Catching Dynamic Heterogeneous User Data for Identity Linkage Learning

Fan Lei, Qiudan Li, Song Sun, Lei Wang, Dajun Zeng

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Benefitting from the development of social platforms, more and more users tend to register multiple accounts on different social networks. Linking user identities across multiple online social networks based on user behavior patterns is considerable for network supervision and information tracking. However, a user's online behavior in a social network is dynamic. The user profile may be changed due to some specific reasons such as user migration or job changes. Thus, catching the dynamics of evolutionary user data and collecting the latest user features are important and challenging issues in the area of user identity linkage. Inspired by deep learning models such as word2vec and Deep Walk, this paper proposes an integrated framework to catch the dynamic user data by supplementing vacant features and updating outdated features in data sources. The framework firstly represents all textual and structural user data into Iow- dimensional latent spaces by utilizing word2vec and DeepWalk, then, integrates different user features and predicts vacant data fields based on late fusion approach and cosine similarity computation. We then explore and evaluate the application of our proposed method in a user identity mapping task. The results proved that our framework can successfully catch the dynamic user data and enhance the performance of identity linkage models by supplementing and updating data sources advance with the times.

Original languageEnglish (US)
Title of host publication2018 International Joint Conference on Neural Networks, IJCNN 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Volume2018-July
ISBN (Electronic)9781509060146
DOIs
StatePublished - Oct 10 2018
Externally publishedYes
Event2018 International Joint Conference on Neural Networks, IJCNN 2018 - Rio de Janeiro, Brazil
Duration: Jul 8 2018Jul 13 2018

Other

Other2018 International Joint Conference on Neural Networks, IJCNN 2018
CountryBrazil
CityRio de Janeiro
Period7/8/187/13/18

Fingerprint

Fusion reactions
Deep learning

Keywords

  • data prediction
  • data supplement
  • deep learning
  • user mapping

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this

Lei, F., Li, Q., Sun, S., Wang, L., & Zeng, D. (2018). Catching Dynamic Heterogeneous User Data for Identity Linkage Learning. In 2018 International Joint Conference on Neural Networks, IJCNN 2018 - Proceedings (Vol. 2018-July). [8489332] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN.2018.8489332

Catching Dynamic Heterogeneous User Data for Identity Linkage Learning. / Lei, Fan; Li, Qiudan; Sun, Song; Wang, Lei; Zeng, Dajun.

2018 International Joint Conference on Neural Networks, IJCNN 2018 - Proceedings. Vol. 2018-July Institute of Electrical and Electronics Engineers Inc., 2018. 8489332.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lei, F, Li, Q, Sun, S, Wang, L & Zeng, D 2018, Catching Dynamic Heterogeneous User Data for Identity Linkage Learning. in 2018 International Joint Conference on Neural Networks, IJCNN 2018 - Proceedings. vol. 2018-July, 8489332, Institute of Electrical and Electronics Engineers Inc., 2018 International Joint Conference on Neural Networks, IJCNN 2018, Rio de Janeiro, Brazil, 7/8/18. https://doi.org/10.1109/IJCNN.2018.8489332
Lei F, Li Q, Sun S, Wang L, Zeng D. Catching Dynamic Heterogeneous User Data for Identity Linkage Learning. In 2018 International Joint Conference on Neural Networks, IJCNN 2018 - Proceedings. Vol. 2018-July. Institute of Electrical and Electronics Engineers Inc. 2018. 8489332 https://doi.org/10.1109/IJCNN.2018.8489332
Lei, Fan ; Li, Qiudan ; Sun, Song ; Wang, Lei ; Zeng, Dajun. / Catching Dynamic Heterogeneous User Data for Identity Linkage Learning. 2018 International Joint Conference on Neural Networks, IJCNN 2018 - Proceedings. Vol. 2018-July Institute of Electrical and Electronics Engineers Inc., 2018.
@inproceedings{04fd7e69b01646e18c853c6555adc9a4,
title = "Catching Dynamic Heterogeneous User Data for Identity Linkage Learning",
abstract = "Benefitting from the development of social platforms, more and more users tend to register multiple accounts on different social networks. Linking user identities across multiple online social networks based on user behavior patterns is considerable for network supervision and information tracking. However, a user's online behavior in a social network is dynamic. The user profile may be changed due to some specific reasons such as user migration or job changes. Thus, catching the dynamics of evolutionary user data and collecting the latest user features are important and challenging issues in the area of user identity linkage. Inspired by deep learning models such as word2vec and Deep Walk, this paper proposes an integrated framework to catch the dynamic user data by supplementing vacant features and updating outdated features in data sources. The framework firstly represents all textual and structural user data into Iow- dimensional latent spaces by utilizing word2vec and DeepWalk, then, integrates different user features and predicts vacant data fields based on late fusion approach and cosine similarity computation. We then explore and evaluate the application of our proposed method in a user identity mapping task. The results proved that our framework can successfully catch the dynamic user data and enhance the performance of identity linkage models by supplementing and updating data sources advance with the times.",
keywords = "data prediction, data supplement, deep learning, user mapping",
author = "Fan Lei and Qiudan Li and Song Sun and Lei Wang and Dajun Zeng",
year = "2018",
month = "10",
day = "10",
doi = "10.1109/IJCNN.2018.8489332",
language = "English (US)",
volume = "2018-July",
booktitle = "2018 International Joint Conference on Neural Networks, IJCNN 2018 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Catching Dynamic Heterogeneous User Data for Identity Linkage Learning

AU - Lei, Fan

AU - Li, Qiudan

AU - Sun, Song

AU - Wang, Lei

AU - Zeng, Dajun

PY - 2018/10/10

Y1 - 2018/10/10

N2 - Benefitting from the development of social platforms, more and more users tend to register multiple accounts on different social networks. Linking user identities across multiple online social networks based on user behavior patterns is considerable for network supervision and information tracking. However, a user's online behavior in a social network is dynamic. The user profile may be changed due to some specific reasons such as user migration or job changes. Thus, catching the dynamics of evolutionary user data and collecting the latest user features are important and challenging issues in the area of user identity linkage. Inspired by deep learning models such as word2vec and Deep Walk, this paper proposes an integrated framework to catch the dynamic user data by supplementing vacant features and updating outdated features in data sources. The framework firstly represents all textual and structural user data into Iow- dimensional latent spaces by utilizing word2vec and DeepWalk, then, integrates different user features and predicts vacant data fields based on late fusion approach and cosine similarity computation. We then explore and evaluate the application of our proposed method in a user identity mapping task. The results proved that our framework can successfully catch the dynamic user data and enhance the performance of identity linkage models by supplementing and updating data sources advance with the times.

AB - Benefitting from the development of social platforms, more and more users tend to register multiple accounts on different social networks. Linking user identities across multiple online social networks based on user behavior patterns is considerable for network supervision and information tracking. However, a user's online behavior in a social network is dynamic. The user profile may be changed due to some specific reasons such as user migration or job changes. Thus, catching the dynamics of evolutionary user data and collecting the latest user features are important and challenging issues in the area of user identity linkage. Inspired by deep learning models such as word2vec and Deep Walk, this paper proposes an integrated framework to catch the dynamic user data by supplementing vacant features and updating outdated features in data sources. The framework firstly represents all textual and structural user data into Iow- dimensional latent spaces by utilizing word2vec and DeepWalk, then, integrates different user features and predicts vacant data fields based on late fusion approach and cosine similarity computation. We then explore and evaluate the application of our proposed method in a user identity mapping task. The results proved that our framework can successfully catch the dynamic user data and enhance the performance of identity linkage models by supplementing and updating data sources advance with the times.

KW - data prediction

KW - data supplement

KW - deep learning

KW - user mapping

UR - http://www.scopus.com/inward/record.url?scp=85056549299&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056549299&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2018.8489332

DO - 10.1109/IJCNN.2018.8489332

M3 - Conference contribution

VL - 2018-July

BT - 2018 International Joint Conference on Neural Networks, IJCNN 2018 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -