User Identity Linkage Research Articles

MFLink: User Identity Linkage Across Online Social Networks via Multimodal Fusion and Adversarial Learning

MFLink: User Identity Linkage Across Online Social Networks via Multimodal Fusion and Adversarial Learning

Exploring Cross-site User Modeling Without Cross-site User Identity Linkage: A Case Study of Content Preference Prediction

Performing user modeling on two or more social media platforms collaboratively and complementing each other (cross-site user modeling) has been a significant problem in the area of social media mining in recent years. The core of this problem is to get to know a person’s identities on multiple platforms and then train user models collaboratively among these platforms. However, for privacy protection, many people do not want their identities on different platforms to be linked and disclosed. For this problem, we set cross-site Content Preference Prediction as a task and propose a cross-site user modeling method without cross-site User Identity Linkage (UIL). The core thought borrowed from privacy-preserving recommender system research is to organize social media identities into groups to hide the identity linkage among platforms. Experiments on real-world datasets suggest that our method outperforms the existing cross-site user modeling methods with cross-site UIL regarding several metrics.

Against linkage: A novel generative face anonymization framework with style diversification

AbstractWith the advent of the digital era, millions of facial images are shared online daily, posing severe privacy threats. Generative face anonymization (GFA) methods generate virtual faces to conceal original identities, protecting sensitive information while preserving utility. However, deep learning based user identity linkage (UIL) methods can link similar faces to the same identity and leverage the linked profiles for malicious purposes, including localization and behaviour prediction. These UIL methods pose a significant challenge to the diversity of virtual faces, a challenge that existing GFA methods have not adequately addressed. To address this research gap, we propose Style Diversification‐based Generative Face Anonymization (SD‐GFA), a framework that generates virtual faces with diverse identities and high visual quality. SD‐GFA features an equalized control module to balance input faces and user‐specified keys, a face generation module with a re‐connection strategy for high‐quality synthesis, and a maximum probability simulation module to enhance diversity. Our experiments demonstrate that SD‐GFA effectively mitigates linkage risk by improving the diversity of virtual faces, while also enhancing their utility and visual quality. This study provides a robust solution to enhance the security of anonymized faces shared on the internet.

EgoMUIL: Enhancing Spatio-Temporal User Identity Linkage in Location-Based Social Networks With Ego-Mo Hypergraph

EgoMUIL: Enhancing Spatio-Temporal User Identity Linkage in Location-Based Social Networks With Ego-Mo Hypergraph

Topic and knowledge-enhanced modeling for edge-enabled IoT user identity linkage across social networks

The Internet of Things (IoT) devices spawn growing diverse social platforms and online data at the network edge, propelling the development of cross-platform applications. To integrate cross-platform data, user identity linkage is envisioned as a promising technique by detecting whether different accounts from multiple social networks belong to the same identity. The profile and social relationship information of IoT users may be inconsistent, which deteriorates the reliability of the effectiveness of identity linkage. To this end, we propose a topic and knowledge-enhanced model for edge-enabled IoT user identity linkage across social networks, named TKM, which conducts feature representation of user generated contents from both post-level and account-level for identity linkage. Specifically, a topic-enhanced method is designed to extract features at the post-level. Meanwhile, we develop an external knowledge-based Siamese neural network for user-generated content alignment at the account-level. Finally, we show the superiority of TKM over existing methods on two real-world datasets. The results demonstrate the improvement in prediction and retrieval performance achieved by utilizing both post-level and account-level representation for identity linkage across social networks.

From Research to Applications: What Can We Extract with Social Media Sensing?

With the constant growth of social media in our daily lives, a huge amount of information is generated online by multiple social networks. However, what can we actually extract with the science of social media sensing? It is a very challenging task to mine meaningful data out of this vast crowdsourcing volume, which also rapidly changes or ends up being misleading. The scope of this paper is to present different approaches that overcome these challenges and utilize social media information from various sources. This work illustrates applications that: improve the performance of architectural design; preserve the cultural heritage; enhance citizen security; provide early detection for disasters; and discover creeping crisis events. A large variety of analyses are presented, including, among other, disaster or crime event detection, user identity linkage, relevance classification, and community detection techniques. The evaluation of the presented methods is also given in this article, proving that they can be practical and valuable in many applications.

MMUIL: enhancing multi-platform user identity linkage with multi-information

MMUIL: enhancing multi-platform user identity linkage with multi-information

DeLink: An Adversarial Framework for Defending against Cross-site User Identity Linkage

Cross-site user identity linkage (UIL) aims to link the identities of the same person across different social media platforms. Social media practitioners and service providers can construct composite user portraits based on cross-site UIL, which helps understand user behavior holistically and conduct accurate recommendations and personalization. However, many social media users expect each profile to stay within the platform where it was created and thus do not want the identities of different platforms to be linked. For this problem, we first investigate the approaches people would like to use to defend against cross-site UIL and the corresponding challenges. Based on the findings, we build an adversarial framework, DeLink, based on the thoughts of adversarial text generation to help people improve their social media screen names to defend against cross-site UIL. DeLink can support both Chinese and English languages and has good generalizability to the varying numbers of social media accounts and different cross-site user identity linkage models. Extensive evaluations validate DeLink’s better performance, including a higher success rate, higher efficiency, less impact on human perception, and capability to defend against different cross-site UIL models.

JORA: Weakly Supervised User Identity Linkage via Jointly Learning to Represent and Align.

The user identity linkage that establishes correspondence between users across networks is a fundamental issue in various social network applications. Efforts have recently been devoted to introducing network embedding techniques that map the different network users into the common representation space, thereby inferring user correspondence based on the similarities of their representations. However, existing studies that separately train the network embedding and space alignment in two stages may lead to conflict between the objectives of the two stages. Besides, the similarities between unlabeled cross-network user pairs are difficult to define and largely impact the result. Moreover, many previous methods still need plenty of labeled aligned user pairs to ensure performance, which may not be available. To address the above problems, we propose to solve the weakly-supervised user identity linkage problem via JOintly learning to Represent and Align, i.e., the JORA model. The architecture of JORA adopts the inductive graph convolutional network (GCN) that learns representations for each network. The model is jointly optimized by the representation learning component and alignment learning component. The former one aims to preserve the similarities between intranetwork users. The latter one aligns the different spaces by a projection function and aims to preserve the similarities between cross-network users. A specific attention mechanism is proposed to learn self-adaptive similarities for unlabeled user pairs during alignment learning and it reduces the error propagation caused by predefined similarities. The joint optimization helps perceive network characteristics during alignment and reduces the number of labeled users required. Experiments conducted on real social networks show that the proposed model achieves significantly better performance than the state-of-the-art methods.

Novel Method of Edge-Removing Walk for Graph Representation in User Identity Linkage

Random-walk-based graph representation methods have been widely applied in User Identity Linkage (UIL) tasks, which links overlapping users between two different social networks. It can help us to obtain more comprehensive portraits of criminals, which is helpful for improving cyberspace governance. Yet, random walk generates a large number of repeating sequences, causing unnecessary computation and storage overhead. This paper proposes a novel method called Edge-Removing Walk (ERW) that can replace random walk in random-walk-based models. It removes edges once they are walked in a walk round to capture the l−hop features without repetition, and it walks the whole graph for several rounds to capture the different kinds of paths starting from a specific node. Experiments proved that ERW can exponentially improve the efficiency for random-walk-based UIL models, even maintaining better performance. We finally generalize ERW into a general User Identity Linkage framework called ERW-UIL and verify its performance.

Efficient User Identity Linkage Based on Aligned Multimodal Features and Temporal Correlation

Efficient User Identity Linkage Based on Aligned Multimodal Features and Temporal Correlation

Semi-Supervised Variational User Identity Linkage via Noise-Aware Self-Learning

User identity linkage, which aims to link identities of a natural person across different social platforms, has attracted increasing research interest recently. Existing approaches usually first embed the identities as deterministic vectors in a shared latent space, and then learn a classifier based on the available annotations. However, the formation and characteristics of real-world social platforms are full of uncertainties, which makes these deterministic embedding based methods sub-optimal. Besides, semi-supervised models utilize the unlabeled data to help capture the intrinsic data distribution. However, the existing semi-supervised linkage methods heavily rely on the heuristically defined similarity measurements to incorporate the innate closeness between labeled and unlabeled samples. Such manually designed assumptions may not be consistent with the actual linkage signals and further introduce the noises. To address the mentioned limitations, in this paper we propose a novel Noise-aware Semi-supervised Variational User Identity Linkage (NSVUIL) model. Specifically, we first propose a novel supervised linkage module to incorporate the available annotations. Each social identity is represented by a Gaussian distribution in the Wasserstein space to simultaneously preserve the fine-grained social profiles and model the uncertainty of identities. Then, a noise-aware self-learning module is designed to faithfully augment the few available annotations, which is capable of filtering noises from the pseudo-labels generated by the supervised module. The filtered reliable candidates are added into the labeled set to provide enhanced training guidance for the next training iteration. Empirically, we evaluate the NSVUIL model over multiple real-world datasets, and the experimental results demonstrate its superiority.

CP-Link: Exploiting Continuous Spatio-Temporal Check-In Patterns for User Identity Linkage

Driven by the large amount of spatio-temporal data obtained from location-based social networks, the implementation of cross-domain user linkage, also known as the User Identity Linkage (UIL), has attracted increasing research attentions. While most of the existing UIL works discretize the spatio-temporal sparse data when identifying encountering or co-located events for UIL, user's distinctive behavior patterns implicit in the ‘`check-in’' spatio-temporal data with continuous nature pave the way for enhancing UIL performance. In this paper, we propose an approach dubbed {\it CP-Link} that exploits user behavior patterns in a continuous way. In CP-Link, the continuous space is divided into irregularly shaped stay regions, and a continuous time-based improved dynamic time warping (IDTW) method is proposed to calculate the similarity. {\color{blue}To bridge the gap between the ideal scenario with ample records and the reality with sparse data}, we adopt the user-associated location frequent pattern (LFP) model to compensate for the sparse deficiency. Extensive experiments conducted on real-world datasets demonstrate the effectiveness and superiority of CP-Link, which outperforms the state of the arts by more than 20% in terms of the AUC.

User Identity Linkage across Social Networks with the Enhancement of Knowledge Graph and Time Decay Function.

Users participate in multiple social networks for different services. User identity linkage aims to predict whether users across different social networks refer to the same person, and it has received significant attention for downstream tasks such as recommendation and user profiling. Recently, researchers proposed measuring the relevance of user-generated content to predict identity linkages of users. However, there are two challenging problems with existing content-based methods: first, barely considering the word similarities of texts is insufficient where the semantical correlations of named entities in the texts are ignored; second, most methods use time discretization technology, where the texts are divided into different time slices, resulting in failure of relevance modeling. To address these issues, we propose a user identity linkage model with the enhancement of a knowledge graph and continuous time decay functions that are designed for mitigating the influence of time discretization. Apart from modeling the correlations of the words, we extract the named entities in the texts and link them into the knowledge graph to capture the correlations of named entities. The semantics of texts are enhanced through the external knowledge of the named entities in the knowledge graph, and the similarity discrimination of the texts is also improved. Furthermore, we propose continuous time decay functions to capture the closeness of the posting time of texts instead of time discretization to avoid the matching error of texts. We conduct experiments on two real public datasets, and the experimental results show that the proposed method outperforms state-of-the-art methods.

Network Alignment across Social Networks Using Multiple Embedding Techniques

Network alignment, which is also known as user identity linkage, is a kind of network analysis task that predicts overlapping users between two different social networks. This research direction has attracted much attention from the research community, and it is considered to be one of the most important research directions in the field of social network analysis. There are many different models for finding users that overlap between two networks, but most of these models use separate and different techniques to solve prediction problems, with very little work that has combined them. In this paper, we propose a method that combines different embedding techniques to solve the network alignment problem. Each association network alignment technique has its advantages and disadvantages, so combining them together will take full advantage and can overcome those disadvantages. Our model combines three-level embedding techniques of text-based user attributes, a graph attention network, a graph-drawing embedding technique, and fuzzy c-mean clustering to embed each piece of network information into a low-dimensional representation. We then project them into a common space by using canonical correlation analysis and compute the similarity matrix between them to make predictions. We tested our network alignment model on two real-life datasets, and the experimental results showed that our method can considerably improve the accuracy by about 10–15% compared to the baseline models. In addition, when experimenting with different ratios of training data, our proposed model could also handle the over-fitting problem effectively.

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

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 information, 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 linkage labels. Then the user-user interactive tensors are constructed as the basis for linking. Using 3D convolutional 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 imbalanced 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.

MAUIL: Multilevel attribute embedding for semisupervised user identity linkage

User identity linkage (UIL) across social networks has recently attracted an increasing amount of attention due to its significant research challenges and practical value. Most of the existing methods use a single method to express different types of attribute features. However, the simplex pattern can neither cover the entire set of different attribute features nor capture the higher-level semantic features in the attribute text. This paper establishes a novel semisupervised model, namely the multilevel attribute embedding for semisupervised user identity linkage (MAUIL), to seek the common user identity across social networks. MAUIL includes two components: multilevel attribute embedding and regularized canonical correlation analysis (RCCA)-based linear projection. Specifically, the text attributes for each network are first divided into three types: character-level, word-level, and topic-level attributes. Second, unsupervised approaches are employed to extract the corresponding three types of text attribute features, and user relationships are embedded as a complimentary feature. All the resultant features are combined to form the final representation of each user. Finally, target social networks are projected into a common correlated space by RCCA with the help of a small number of prematched user pairs. We demonstrate the superiority of the proposed method over state-of-the-art methods through extensive experiments on two real-world datasets. All the datasets and codes are publicly available online.11https://github.com/ChenBaiyang/MAUIL.

User Identity Linkage via Co-Attentive Neural Network From Heterogeneous Mobility Data

Online services are playing critical roles in almost all aspects of users’ life. Users usually have multiple online identities (IDs) in different online services. In order to fuse the separated user data in multiple services for better business intelligence, it is critical for service providers to link online IDs belonging to the same user. On the other hand, the popularity of mobile networks and GPS-equipped smart devices have provided a generic way to link IDs, i.e., utilizing the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">mobility traces</i> of IDs. However, linking IDs based on their mobility traces has been a challenging problem due to the highly heterogeneous, incomplete and noisy mobility data across services. In this paper, we propose <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DPLink</i> , an end-to-end deep learning based framework, to complete the user identity linkage task for heterogeneous mobility data collected from different services with different properties. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DPLink</i> is made up by a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">feature extractor</i> including a location encoder and a trajectory encoder to extract representative features from trajectory and a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">comparator</i> to compare and decide whether to link two trajectories as the same user. Particularly, we propose a pre-training strategy with a simple task to train the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DPLink</i> model to overcome the training difficulties introduced by the highly heterogeneous nature of different source mobility data. Besides, we introduce a multi-modal embedding network and a co-attention mechanism in <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DPLink</i> to deal with the low-quality problem of mobility data. By conducting extensive experiments on two real-life ground-truth mobility datasets with eight baselines, we demonstrate that <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DPLink</i> outperforms the state-of-the-art solutions by more than 15 percent in terms of hit-precision. Moreover, it is expandable to add external geographical context data and works stably with heterogeneous noisy mobility traces.

Social media user identity linkage by graphic content comparison

The article proposes a new approach to comparing accounts of the social media “VKontakte” and “Instagram” to determine those accounts which belong to the same user. The approach is based on the comparison of graphic content; the novelty of the approach consists in combining several methods for matching graphic content, also for the first time a method is proposed for matching accounts of the mentioned social media. The proposed method combines three methods of matching graphic content: by extracting the faces of the account users from the photos in the account and matching them, by matching all faces in both accounts, and by pairwise comparison of images to determine the same images in both accounts using the perceptual pHash method. The described method was tested on a dataset of more than 8,000 pairs of accounts. According to the results of the experiment, the value of the F1-score metric reached 0.87. The practical significance lies in automating the comparison of user accounts in various social networks by implementing of the developed algorithm in the prototype of the software package. A further direction for research lies in expanding the set of data and attributes of profiles considered for comparison. The results can be introduced into a software package for the analysis of the security of a user of information systems against social engineering attacks. It seems promising to combine the obtained findings with account matching methods based on the structural similarity of social graphs.

User Identity Linkage for Different Behavioral Patterns across Domains

As customers use and benefit from multiple services, a large amount of customer data are accumulating daily. Connecting a customer's identity on a service with her identity on a different service, known as user identity linkage (UIL), enables a comprehensive understanding of users in a variety of real-world applications. The difficulties of UIL tasks in marketing applications are mainly the lack of user demographics and diverse user behavioral patterns, which differs from UIL tasks in social networking services that previous UIL methods have mainly been used to tackle. In this paper, we propose a novel method for UIL for different behavioral patterns to determine whether two given behavioral histories come from the same user without using any user demographics. Our proposed method links users by using natural language processing to efficiently characterize user intrinsic features and bridging the gap between two different behavioral patterns of the same user. We conducted experiments to evaluate our proposed method for three real-world open source datasets and observed that it successfully linked users compared to conventional UIL methods.