Identifying users across social networks based on dynamic core interests

Nie, Yuanping; Jia, Yan; Li, Shudong; Xiang, Zhu; Li, Aiping; Zhou, Bin

doi:10.1016/j.neucom.2015.10.147

Cited by 95 publications

(41 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are many UIL methods adopting the supervised approach [5,6,[10][11][12][14][15][16]22]. They can be broadly classified into those using classification techniques and others using embedding techniques.…”

Section: Supervised and Semi-supervised Approachesmentioning

confidence: 99%

Retrofitting Embeddings for Unsupervised User Identity Linkage

Zhou

Lim

Lee

et al. 2020

Advances in Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

User Identity Linkage (UIL) is the problem of matching user identities across multiple online social networks (OSNs) which belong to the same person. The solutions to UIL problem facilitate cross-platform research on OSN users and enable many useful applications such as user profiling and recommendation. As the UIL labeled data are often lacking and costly to obtain, learning user embeddings for matching user identities using an unsupervised approach is therefore highly desired. In this paper, we propose a novel unsupervised UIL framework for enhancing existing user embedding-based UIL methods. Our proposed framework incorporates two key ideas, user-discriminative features and retrofitting embedding. The user-discriminative features enable us to differentiate a specific user identity from other users in its OSN. From the userdiscriminative features, we derive pairs of similar user identities across OSNs for retrofitting the base user embeddings of existing UIL methods. Through extensive experiments on three real-world OSN datasets, we show that our framework can leverage user-discriminative features to improve the accuracy of different user embedding-based UIL methods significantly. The quantum of improvement can also be surprisingly good even for existing UIL methods with very poor matching accuracy. Electronic supplementary materialThe online version of this chapter (https://

show abstract

Section: Supervised and Semi-supervised Approachesmentioning

confidence: 99%

Retrofitting Embeddings for Unsupervised User Identity Linkage

Zhou

Lim

Lee

et al. 2020

Advances in Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

show abstract

“…Li and others analyzed the username naming mode in different social networks, used the redundant information in the user name to establish the user name characteristics, and finally used the supervised machine learning method for identity recognition [14]. Nie et al identified the user based on the status of the user's published status, and proposed a method to analyze the dynamics of user interest [15]. Almishari et al proposed a method of using writing style for identification [16].…”

Section: Cross-social-network User Identificationmentioning

confidence: 99%

Cross-social-network Interconnection Model Based on Bridge Community

Hu¹,

dong²

2019

Proceedings of the 12th EAI International Conference on Mobile Multimedia Communications, Mobimedia 2019, 29th - 30th Jun 2019,

View full text Add to dashboard Cite

As users participate in many online social networks (OSNs), connecting different social networks has become the latest task that researchers are focusing on. The analysis of user behavior needs to mine user information from multiple social networks, obtain more accurate information through association matching to analyze and predict, and improve the attributes of users' multiple social networks. Through the mining and analysis of user information, the interconnection of information dissemination of multiple social networks is realized. This paper firstly sorts the importance of user nodes in multi-social networks, and finds important nodes and secondarily important nodes to form the initial bridge community; then we build bridge user links through similarity matching of the users in the bridge community; finally, we propose cross-social-network interconnection model based on bridge community to enhance the structural interconnection between multiple social networks.

show abstract

“…A probabilistic graphical model for topic and preference discovery on social media is studied in [24], where user preferences are modelled based on user access logs. To identify users across social networks, Nie et al [25] made use of the profile information provided by users and the content and structural information of users to define user similarity.…”

Section: Related Workmentioning

confidence: 99%