AsyLink: user identity linkage from text to geo-location via sparse labeled data

doi:10.1016/j.neucom.2022.10.027

	AsyLink: user identity linkage from text to geo-location via sparse labeled data
	Shao, Jiangli 1,2; Wang, Yongqing 1; Gao, Hao 1,2; Shi, Boshen 1,2; Shen, Huawei 1; Cheng, Xueqi 1
	2023
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
卷号	515 页码:174-184
摘要	User Identity Linkage (UIL) aims to reveal the correspondence among account pairs across different social platforms. It has been a popular but challenging task in recent years as complex application scenarios have emerged. Existing UIL methods mainly formalize a classification problem based on symmetric infor-mation, but these techniques are hard to apply to asymmetric, sparsely labeled, and imbalanced data. To combat the challenges, we propose a novel UIL framework (AsyLink) with asymmetric information in text and geographic forms. AsyLink first uses topic modeling technologies to associate words and locations, where external text-location pairs can be conveniently introduced to reduce bias caused by sparse link-age labels. Then the user-user interactive tensors are constructed as the basis for linking. Using 3D con-volutional neural networks, matching patterns in user-user interactive tensors are captured, and final predictions are based on the extracted features. Meanwhile, instead of regular classification loss, the ranking loss is introduced to predict the best answer among candidates, which is conducive to imbal-anced classification. Experiments performed on four real-world datasets indicate that AsyLink achieves state-of-the-art performances and has great potential for real-world applications. (c) 2022 Elsevier B.V. All rights reserved.
关键词	User identity linkage User -generated text Geo-location
DOI	10.1016/j.neucom.2022.10.027
收录类别	SCI
语种	英语
资助项目	National Natural Science Founda-tion of China ; National Social Science Fund of China ; Beijing Nova Program ; China Postdoctoral Science Foundation ; [U21B2046,61902380] ; [19ZDA329] ; [Z201100006820061] ; [2022M713206]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000877611700010
出版者	ELSEVIER
引用统计	被引频次：11[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/20237
专题	中国科学院计算技术研究所期刊论文
通讯作者	Wang, Yongqing
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Data Intelligence Syst Res Ctr, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Shao, Jiangli,Wang, Yongqing,Gao, Hao,et al. AsyLink: user identity linkage from text to geo-location via sparse labeled data[J]. NEUROCOMPUTING,2023,515:174-184.
APA	Shao, Jiangli,Wang, Yongqing,Gao, Hao,Shi, Boshen,Shen, Huawei,&Cheng, Xueqi.(2023).AsyLink: user identity linkage from text to geo-location via sparse labeled data.NEUROCOMPUTING,515,174-184.
MLA	Shao, Jiangli,et al."AsyLink: user identity linkage from text to geo-location via sparse labeled data".NEUROCOMPUTING 515(2023):174-184.