The multi-interest sequential recommendation system analyzes users' historical behaviors to construct multiple representations of interests, thus better capturing their diverse interests. Although existing methods perform well in recommendation tasks, most of them construct multiple user interests based on static graphs. They fail to consider the evolving nature of user interests and the semantic relations between consecutive items. They overlook the evolving nature of user interests and the dependencies between consecutive items. Therefore, we propose Meta-Path aware Dynamic Multi-Interest Learning for sequential recommendation (MPDMI). MPDMI constructs multi-interest representations of users that evolve with behavior sequences by capturing meta-paths between consecutive interactions in a dynamic graph. This method not only accurately captures the dynamic changes in user preferences but also extracts dependencies between consecutive items. We conduct extensive experiments on three benchmark datasets, and the results show that MPDMI significantly outperforms several state-of-the-art methods, demonstrating its great potential in handling the dynamic evolution of user multi-interests. The implementations are available at https://github.com/MPDMI/MPDMI.

Recommendation systems face significant challenges in effectively modeling complex multi-behavioral user interactions, such as viewing, adding to cart, and purchasing. Existing methods often treat various behaviors collectively, overlooking the noise and redundancy between them. In this paper, we propose a novel multi-behavior graph recommendation model that integrates sequential information, named MBGSI (Multi-Behavior Graph Recommendation with Fusion of Sequential Information). Our approach constructs separate user-item graphs for distinct behaviors and employs a projection mechanism to mitigate interbehavior noise, enhancing the extraction of behavior-specific factors. Moreover, we incorporate sequential user-item interactions into the model to capture temporal patterns and enrich embeddings of users and items. The attention module in the transformer architecture is further optimized by introducing behavior distribution tables and behavior pair position factors to improve the calculation of attention scores. The refined user and item representations are then leveraged to predict users’ future interactions. To the best of our knowledge, this is the first exploration of fusing sequence information with multi-behavior graphs for enhanced recommendation performance. Extensive experiments on three benchmark datasets demonstrate that MBGSI achieves superior results compared to state-of-the-art baselines.

Knowledge graph (KG) containing various types of auxiliary information about users and items has been proven to be effective to improve the performance of recommendation. Existing KG aware methods usually exploit entity representation by learning the structural and semantic paths information by assuming that KG has been fully constructed or learning the entity embeddings with interactions occurring in succession. Although these works have achieved convincing results, most of them ignore the semantic paths information between two learned entities directly involved in interactions even if they have considered the dynamic learning of knowledge graph. However, both the semantic path information between the involved entities and the occurring interaction itself can refine their representations. To this end, we propose a temporal Knowledge Graph incremental Evolution model for sequential Recommendation (KGER), which learns and updates the representations of user and item by not only considering the influence of interaction itself, but also high-order semantic paths information between them with the interactions happening. Specifically, different length semantic paths are automatically extracted between user-item pairs when an interaction occurs. Then we update the semantic representations of the two entities by considering the influences brought from interaction itself and high-order semantic paths information between two involved entities. We employ recurrent neural network and standard multi-layer perceptron (MLP) to capture different length semantic paths and interaction itself information, respectively. Finally, we use MLP to train the model after seamlessly integrating these influences into a unified representation. We conduct experiments on three real-world datasets to demonstrate the superiority of our proposed model over all state-of-the-art baselines.

The proliferation of social networks has made anomaly detection a critical safeguard against escalating threats of online fraud and unauthorized access. By leveraging the inherent relational topology of social networks, graph-based detection methods have emerged as a powerful paradigm, exploiting explicit inter-node dependencies for enhanced detection performance. However, existing methods still face three key challenges: class imbalance, ambiguous anomaly definitions, and noise introduced by uniform neighbor treatment. To overcome these limitations, we propose PAAR-a Preprocessing- and Attention-Aggregation-based Refined Graph Neural Network. PAAR comprises three main components: (1) a Preprocessing module that addresses class imbalance via combined over- and under-sampling strategies; (2) a Dynamic Weight Allocation module that improves detection accuracy by adaptively weighting each node’s neighbors; and (3) a Refinement module that boosts model expressiveness through iterative retraining with high-confidence nodes identified in initial predictions. Extensive experiments on the Amazon and YelpChi datasets demonstrate the superiority of PAAR over nine competitive baselines, surpassing FRAUDRE by 7% and CARE-GNN by 8% in AUC.

Multi-interest recommendation is to predict the next item by representing diversity of a user preference with multiple interest embeddings. Although existing methods have achieved convincing results in recommendation tasks, they ignore the continuously changing relations of no-adjacent items in a sequence. In this paper, we focus on how to fully capture the changing relations when capturing the user multi-interest representations. Specifically, we propose a novel dynamic graph cluster-based multi-interest model named MDGR, which not only comprehensively explores the real changing item relations between no-adjacent items by iteratively constructing and continuously optimizing interest sub-graph to update the multiple interest embeddings but also collaborates temporal information and interest weight to model the interactive behaviors of users and items.Our model iteratively constructs and continuously optimizes the interest sub-graph by comprehensively adopting dynamic graph cluster to explore the item relations in sequences. That is beneficial to dynamically model user multiple interests. Furthermore, we employ the attention module to extract different influence of various interest embeddings. Finally, we use the refined item embedding and the final multi-interest embeddings to retrieval the next item that a user is most likely to interact with. To the best of our knowledge, this is the first attempt to explore multi-interest embeddings by iteratively constructing and continuously optimizing the interest sub-graph. Extensive experiments on three popular benchmark datasets demonstrate that MDGR outperforms several state-of-the-art methods.

Graph anomaly detection has gained significant research interest across various domains. Due to the lack of labeled data, contrastive learning has been applied in detecting anomalies and various contrastive strategies have been initiated. However, these methods might force two instances (e.g., node-level and subgraph-level representations) with different category labels to be consistent during model training, which can adversely impact the model robustness. Also, they extract node-level representations only based on node attributes, which are inadequate in reflecting the information of the structural anomaly. To tackle this problem, we present a Graph-enhanced multi-scale Contrastive Learning framework for Anomaly Detection, GCLAD. In this framework, we design a diffusion probabilistic model-based graph enhancement module to adaptively manipulate neighbors to generate enhanced graphs, which can efficiently enhance subgraph-level representations and alleviate the inconsistent problem. Further, we present a multi-scale contrastive module where we introduce meta-paths to exploit a few relevant neighbors to boost node-level representations, and build the multi-scale contrastive losses to promote anomaly detection performance. Experimental results demonstrate the superiority of GCLAD compared with state-of-the-art baselines.

Graph anomaly detection is critical in domains such as healthcare and economics, where identifying deviations can prevent substantial losses. Existing unsupervised approaches strive to learn a single model capable of detecting both attribute and structural anomalies. However, they confront the tug-of-war problem between two distinct types of anomalies, resulting in suboptimal performance. This work presents TripleAD, a mutual distillation-based triple-channel graph anomaly detection framework. It includes three estimation modules to identify the attribute, structural, and mixed anomalies while mitigating the interference between different types of anomalies. In the first channel, we design a multiscale attribute estimation module to capture extensive node interactions and ameliorate the over-smoothing issue. To better identify structural anomalies, we introduce a link-enhanced structure estimation module in the second channel that facilitates information flow to topologically isolated nodes. The third channel is powered by an attribute-mixed curvature, a new indicator that encapsulates both attribute and structural information for discriminating mixed anomalies. Moreover, a mutual distillation strategy is introduced to encourage communication and collaboration between the three channels. Extensive experiments demonstrate the effectiveness of the proposed TripleAD model against strong baselines.

The success of graph neural networks (GNNs) has spurred numerous new works leveraging GNNs for modeling multivariate time series anomaly detection. Despite their achieved performance improvements, most of them only consider static graph to describe the spatial-temporal dependencies between time series. Moreover, existing works neglect the time and scale-changing structures of time series. In this work, we propose MDGAD, a novel multi-scale dynamic graph structure learning approach for time series anomaly detection. We design a multi-scale graph structure learning module that captures the complex correlations among time series, constructing an evolving graph at each scale. Meanwhile, an anomaly detector is used to combine bilateral prediction errors to detect abnormal data. Experiments conducted on two time series datasets demonstrate the effectiveness of MDGAD.

Graph anomaly detection has gained significant research interest across various domains. Due to the lack of labeled data, contrastive learning has been applied in detecting anomalies and various scales of contrastive strategies have been initiated. However, these methods might force two instances (e.g., node-level and subgraph-level representations) with different category labels to be consistent during model training, which can adversely impact the model robustness. To tackle this problem, we present a novel contrastive learning framework with the Diffusion model-based graph Enhancement module for Graph Anomaly Detection, DEGAD. In this framework, we design a diffusion model-based graph enhancement module to manipulate neighbors to generate enhanced graphs, which can efficiently alleviate the inconsistent problem. Further, based on the enhanced graphs, we present a multi-scale contrastive module to discriminate anomalies. Experimental results demonstrate the superiority of our model.

Graph anomaly detection has received remarkable research interests, and various techniques have been employed for enhancing detection performance. However, existing models tend to learn dataset-specific spurious correlations based on statistical associations. A well-trained model might suffer from performance degradation when applied to newly observed nodes with different environments. To handle this situation, we propose CounterFactual Graph Anomaly Detection model, CFGAD. In this model, we design a gradient-based separator to disentangle node features into class features and environment features. Then, we present a weight-varying diffusion model to combine class features and environment features from different nodes to generate counterfactual samples. These counterfactual samples will be adopted to enhance model robustness. Comprehensive experiments demonstrate the effectiveness of our CFGAD.

Graph-level anomaly detection is significant in diverse domains. To improve detection performance, counterfactual graphs have been exploited to benefit the generalization capacity by learning causal relations. Most existing studies directly introduce perturbations (e.g., flipping edges) to generate counterfactual graphs, which are prone to alter the semantics of generated examples and make them off the data manifold, resulting in sub-optimal performance. To address these issues, we propose a novel approach, Motif-consistent Counterfactuals with Adversarial Refinement (MotifCAR), for graph-level anomaly detection. The model combines the motif of one graph, the core subgraph containing the identification (category) information, and the contextual subgraph (non-motif) of another graph to produce a raw counterfactual graph. However, the produced raw graph might be distorted and cannot satisfy the important counterfactual properties: Realism, Validity, Proximity and Sparsity. Towards that, we present a Generative Adversarial Network (GAN)-based graph optimizer to refine the raw counterfactual graphs. It adopts the discriminator to guide the generator to generate graphs close to realistic data, i.e., meet the property Realism. Further, we design the motif consistency to force the motif of the generated graphs to be consistent with the realistic graphs, meeting the property Validity. Also, we devise the contextual loss and connection loss to control the contextual subgraph and the newly added links to meet the properties Proximity and Sparsity. As a result, the model can generate high-quality counterfactual graphs. Experiments demonstrate the superiority of MotifCAR.

WiFi channel state information (CSI)-based activity recognition has sparked numerous studies due to its widespread availability and privacy protection. However, when applied in practical applications, general CSI-based recognition models may face challenges related to the limited generalization capability, since individuals with different behavior habits will cause various fluctuations in the CSI data and it is difficult to gather enough training data to cover all kinds of motion habits. To tackle this problem, we design a diffusion model-based contrastive learning framework for human activity recognition (CLAR) using WiFi CSI. On the basis of the contrastive learning framework, we primarily introduce two components for CLAR to enhance the CSI-based activity recognition. To generate diverse augmented data and complement limited training data, we propose a diffusion model-based time series-specific augmentation model. In contrast to typical diffusion models that directly apply conditions to the generative process, potentially resulting in distorted CSI data, our tailored model dissects these condition into the high-frequency and low-frequency components, and then applies these conditions to the generative process with varying weights. This can alleviate the data distortion and yield high-quality augmented data. To efficiently capture the difference of the sample importance, we present an adaptive weight algorithm. Different from the typical contrastive learning methods which equally consider all the training samples, this algorithm adaptively adjusts the weights of positive sample pairs for learning better data representations. The experiments suggest that the CLAR achieves significant gains compared to the state-of-the-art methods.

A critical aspect of graph neural networks (GNNs) is to enhance the node representations by aggregating node neighborhood information. However, when detecting anomalies, the representations of abnormal nodes are prone to be averaged by normal neighbors, making the learned anomaly representations less distinguishable. To tackle this issue, we propose an unsupervised counterfactual data augmentation method for graph anomaly detection (CAGAD) that introduces a graph pointer neural network as the heterophilic node detector to identify potential anomalies whose neighborhoods are normal-node-dominant. For each identified potential anomaly, we design a graph-specific diffusion model to translate a part of its neighbors, which are probably normal, into anomalous ones. At last, we involve these translated neighbors in GNN neighborhood aggregation to produce counterfactual representations of anomalies. Through aggregating the translated anomalous neighbors, counterfactual representations become more distinguishable and further advocate detection performance. The experimental results on four datasets demonstrate that CAGAD significantly outperforms strong baselines, with an average improvement of 2.35% on F1, 2.53% on AUC-ROC, and 2.79% on AUC-PR.

Modeling the dynamic interactions between users and items on knowledge graphs is crucial for improving the accuracy of recommendation. Although existing methods have made great progress in modeling the dynamic knowledge graphs for recommendation, they usually only consider the mutual influence between users and items involved in the interactions, and ignore the influence propagation from the interacting nodes (i.e., users and items) on dynamic knowledge graphs. In this article, we propose an influence propagation-enhanced deep co-evolutionary method for recommendation, which can capture not only the direct mutual influence between interacting users and items but also influence propagation from multiple interacting nodes to their high-order neighbors at the same time on the dynamic knowledge graph. Specifically, the proposed model consists of two main components: the direct mutual influence component and the influence propagation component. The former captures direct interaction influence between the interacting users and items to generate the effective representations for them. The latter refines their representations via aggregating the interaction influence propagated from multiple interacting nodes. In this process, a neighbor selection mechanism is designed for selecting more effective propagation influence, which can significantly reduce the computational cost and accelerate the training. Finally, the refined representations of users and items are used to predict which item the user is most likely to interact with. The experimental results on three real-world datasets illustrate that the effectiveness and robustness of PIDKG outperform all state-of-the-art baselines and the efficiency of it is faster than most comparative baselines.

Sequential recommendation is to predict the next item by capturing the item transformation in the user historical sequences. Although existing methods have achieved convincing results in recommendation tasks, they ignore the relation between discontinuous items within sequences or those across different sequences. In this paper, we focus on how to fully capture the potential item relation within and across sequences. Specifically, we propose a novel graph collaborative optimization-based method named GOSR, which not only comprehensively explores the real item relation from many perspectives by constructing and optimizing the item relation graph but also collaborates user-item interaction graph to model the interactive behaviors of users and items. Our model converts the loose item sequences to a tight item relation graph and continuously optimize the graph by comprehensively considering the item relation within and across sequences. That is beneficial to dynamically capture the actual item relation. Furthermore, we employ the attention module to extract the long short-term preferences and characters of users and items by collaborating the user-item interaction graph. Finally, we use the refined representations of users and items to predict the next item that a user is most likely to interact with. To the best of our knowledge, this is the first attempt to explore the item relation by constructing and optimizing the item relation graph for better recommendation. Extensive experiments on three popular benchmark datasets demonstrate that GOSR outperforms several state-of-the-art methods.

Existing anomaly detection models for time series are primarily trained with normal-point-dominant data and would become ineffective when anomalous points intensively occur in certain episodes. To solve this problem, we propose a new approach, called DiffAD, from the perspective of time series imputation. Unlike previous prediction- and reconstruction-based methods that adopt either partial or complete data as observed values for estimation, DiffAD uses a density ratio-based strategy to select normal observations flexibly that can easily adapt to the anomaly concentration scenarios. To alleviate the model bias problem in the presence of anomaly concentration, we design a new denoising diffusion-based imputation method to enhance the imputation performance of missing values with conditional weight-incremental diffusion, which can preserve the information of observed values and substantially improves data generation quality for stable anomaly detection. Besides, we customize a multi-scale state space model to capture the long-term dependencies across episodes with different anomaly patterns. Extensive experimental results on real-world datasets show that DiffAD performs better than state-of-the-art benchmarks.

WiFi channel state information (CSI)-based activity recognition has initiated a great many studies because of wide availability and privacy protection. However, general recognition approaches still struggle to generalize beyond the source domain of training data, i.e., well-trained models might not be suitable to target data with unseen subjects or environments. Existing solutions, such as few-shot learning-based and data augmentation-based approaches, either require a few labeled target samples which is difficult to be collected, especially, for old target users, or inappropriately treat augmented samples with different amounts of noise. To overcome these limitations, we propose a Mean Teacher-based cross-domain human activity recognition framework using WiFi CSI, WiTeacher. In this framework, to address the shift between source and target domains, we built a label smoothing-based classification loss, where the input data are the target-like samples generated by StyleGAN, and corresponding label values are dynamically adjusted by our designed adaptive label smoothing method. To enhance the model robustness, we devise a sample relation-based consistency regularization term to keep the distances of the two samples with and without perturbations invariant, which can exploit the relationships between samples to improve recognition performance. The experiments illustrate that WiTeacher achieves obvious gains without requiring any annotation data from the target domain.

Graph anomaly detection is attracting remarkable multidisciplinary research interests ranging from finance, healthcare, and social network analysis. Recent advances on graph neural networks have substantially improved the detection performance via semi-supervised representation learning. However, prior work suggests that deep graph-based methods tend to learn spurious correlations. As a result, they fail to generalize beyond training data distribution. In this article, we aim to identify structural and contextual anomaly nodes in an attributed graph. Based on our preliminary data analyses, spurious correlations can be eliminated with causal subgraph interventions. Therefore, we propose a new graph-based anomaly detection model that can learn causal relations for anomaly detection while generalizing to new environments. To handle situations with varying environments, we steer the generative model to manufacture synthetic environment features, which are exerted on realistic subgraphs to generate counterfactual subgraphs. Further, these counterfactual subgraphs help a few-shot anomaly detection model learn transferable and causal relations across different environments. The experiments on three real-world attributed graphs show that the proposed approach achieves the best performance compared to the state-of-the-art baselines and learns robust causal representations resistant to noises and spurious correlations.

Extracting valuable activity segments from continuously received sensor data is a key step for many downstream applications such as activity recognition, trajectory prediction, and gesture recognition. Numerous unsupervised and supervised approaches have been proposed for activity segmentation. However, current unsupervised methods generally suffer from subject and environment-dependent problems, and supervised methods require a great many labeled data which is time-consuming and expensive to be collected. To address these issues, we propose a Self-supervised Few-shot Time-series Segmentation framework called SFTSeg, which introduces few-shot learning to conduct activity segmentation only relying on several labeled target samples. To be applicable to time-series data, we design a line-level data augmentation method to build a consistency regularization for the few-shot learning framework, which can augment limited labeled target samples to enhance generalization capacity of the model. Also, we devise a time series-specific pretext task to construct a self-supervised loss with adaptive weighting, which can adopt unlabeled target data to enable the model to learn characteristics of the target data and further improve segmentation performance. The experiments illustrated that SFTSeg achieves obvious gains compared to state-of-the-art methods.

Discovering interesting yet unvisited point-of-interests (POIs) is among the most practical applications but challenging problems in location-based social networks (LBSNs). Popular approaches face several issues, such as data sparsity and difficulties in modeling latent nonlinearity between users and POIs. Furthermore, the uncertainty in LBSNs poses additional obstacles to learning good representations of users’ general and current interests. To effectively address these issues, we postulate that fusing multiple sources of information is paramount. Toward that, we propose a novel deep generative recommender system—Wasserstein autoencoder for POI recommendation (WaPOIR). It unifies the information from users’ personal preference, social influence, and geographical data, and captures users’ general interests from historical check-ins, while modeling users’ current interests from recently visited POIs. Unlike previous methods, WaPOIR learns the latent distribution of data in the Wasserstein space as a potential representation for each POI and each user in LBSNs. This enables simultaneous maintenance of social and POI interactions and modeling the uncertainty of their relationships. WaPOIR is a stochastic recommendation approach that allows Bayesian inference and approximation of variational posterior distribution. Extensive experiments conducted on real-world LBSN datasets demonstrate that WaPOIR achieves better performance over the state-of-the-art approaches.

Pinpointing the geographic location of an IP address is important for a range of location-aware applications spanning from targeted advertising to fraud prevention. The majority of traditional measurement-based and recent learning-based methods either focus on the efficient employment of topology or utilize data mining to find clues of the target IP in publicly available sources. Motivated by the limitations in existing works, we propose a novel framework named GraphGeo, which provides a complete processing methodology for street-level IP geolocation with the application of graph neural networks. It incorporates IP hosts knowledge and kinds of neighborhood relationships into the graph to infer spatial topology for high-quality geolocation prediction. We explicitly consider and alleviate the negative impact of uncertainty caused by network jitter and congestion, which are pervasive in complicated network environments. Extensive evaluations across three large-scale real-world datasets demonstrate that GraphGeo significantly reduces the geolocation errors compared to the state-of-the-art methods. Moreover, the proposed framework has been deployed on the web platform as an online service for 6 months.

Due to its nonintrusive character, WiFi channel state information (CSI)-based activity recognition has attracted tremendous attention in recent years. Since activity recognition performance heavily relies on activity segmentation results, a number of activity segmentation methods have been designed, and most of them focus on seeking optimal thresholds to segment activities. However, these threshold-based methods are strongly dependent on designers' experience and might suffer from performance decline when applying to the scenario, including both fine-grained and coarse-grained activities. To address these challenges, we present DeepSeg, a deep learning-based activity segmentation framework for activity recognition using WiFi signals. In this framework, we transform segmentation tasks into classification problems and propose a CNN-based activity segmentation algorithm, which can reduce the dependence on experience and address the performance degradation problem. To further enhance the overall performance, we design a feedback mechanism, where the segmentation algorithm is refined based on the feedback computed using activity recognition results. The experiments demonstrate that DeepSeg acquires remarkable gains compared with state-of-the-art approaches.

As a cornerstone service for many Internet of Things applications, channel state information (CSI)-based activity recognition has received immense attention over recent years. However, recognition performance of general approaches might significantly decrease when applying the trained model to the left-out user whose CSI data are not used for model training. To overcome this challenge, we propose a semi-supervised generative adversarial network (GAN) for CSI-based activity recognition (CsiGAN). Based on the general semi-supervised GANs, we mainly design three components for CsiGAN to meet the scenarios that unlabeled data from left-out users are very limited and enhance recognition performance: 1) we introduce a new complement generator, which can use limited unlabeled data to produce diverse fake samples for training a robust discriminator; 2) for the discriminator, we change the number of probability outputs from k + 1 into 2k + 1 (here, k is the number of categories), which can help to obtain the correct decision boundary for each category; and 3) based on the introduced generator, we propose a manifold regularization, which can stabilize the learning process. The experiments suggest that CsiGAN attains significant gains compared to the state-of-the-art methods.

Traditional supervised keyphrase extraction models depend on the features of labelled keyphrases while prevailing unsupervised models mainly rely on structure of the word graph, with candidate words as nodes and edges capturing the co-occurrence information between words. However, systematically integrating all these multidimensional heterogeneous information into a unified model is relatively unexplored. In this paper, we focus on how to effectively exploit multidimensional information to improve the keyphrase extraction performance (MIKE). Specifically, we propose a random-walk parametric model, MIKE, that learns the latent representation for a candidate keyphrase that captures the mutual influences among all information, and simultaneously optimizes the parameters and ranking scores of candidates in the word graph. We use the gradient-descent algorithm to optimize our model and show the comprehensive experiments with two publicly-available WWW and KDD datasets in Computer Science. Experimental results demonstrate that our approach significantly outperforms the state-of-the-art graph-based keyphrase extraction approaches.

Modelling users’ dynamic preference for personalized temporal recommendation has been a hot research topic. Traditional dynamic recommendation models divide a user’s interaction history into fixed-sized windows to learn the user’s evolving preference. This strategy however worsens the issue of data sparsity in that some sessions may have very little or even no interaction for preference inference. To alleviate the data sparsity issue and avoid errors due to data imputation that is commonly adopted by existing models, a novel session-based dynamic recommendation model that divides a user’s interaction history with dynamic window size is proposed. An empirical study on the users’ activity life cycles using real-world dataset is conducted to demonstrate the nonuniformness and aggregation of the users’ behavior patterns on the time dimension. Based on the study, a user’s interaction history is divided with dynamic temporal window size by using dynamic clustering. The user’s evolving profile is then constructed by modeling her preference in each session using Latent Dirichlet Allocation (LDA) and a time sensitive weighting scheme. Our dynamic model is designed for two major recommendation tasks: (1) top-N recommendation, which is provided by measuring the relevance of probabilistic topic distribution between the user’s profile in the next temporal domain and each candidate item, (2) rating prediction that is achieved by finding K nearest user/item neighbors based the similarity of probabilistic topic distribution between users/items. Extensive empirical experiments over two real datasets demonstrate the effectiveness and superiority of our method by comparing to representative temporal dynamic methods.

This work presents a novel writing style-based approach to detect multi-account users on User-Generated Content (UGC) sites. Unlike existing works which emphasize feasibility and privacy leakage, we focus on precise writing style-based multi-account detection. Specifically, we leverage a one-class classification-based approach to detect multi-account behaviors, in which a mutual similarity measurement is defined to increase detection precision. In addition to traditional features used in writing style detection, we also extract bigrams, trigrams, part-of-speech, and grammatical relations. We evaluate our methodology based on datasets crawled from 3 popular OSNs (i.e., Twitter, Facebook, and Google+). Experimental results demonstrate that compared with the most recent achievements, our method not only improves the average detection precision to almost 90%, but also increases both recall and F-measure to 90% and even better.

Understanding the behavior and characteristics of web users is valuable when improving information dissemination, designing recommendation systems, and so on. In this work, we explore various methods of predicting the ratio of male viewers to female viewers on YouTube. First, we propose and examine two hypotheses relating to audience consistency and topic consistency. The former means that videos made by the same authors tend to have similar male‐to‐female audience ratios, whereas the latter means that videos with similar topics tend to have similar audience gender ratios. To predict the audience gender ratio before video publication, two features based on these two hypotheses and other features are used in multiple linear regression (MLR) and support vector regression (SVR). We find that these two features are the key indicators of audience gender, whereas other features, such as gender of the user and duration of the video, have limited relationships. Second, another method is explored to predict the audience gender ratio. Specifically, we use the early comments collected after video publication to predict the ratio via simple linear regression (SLR). The experiments indicate that this model can achieve better performance by using a few early comments. We also observe that the correlation between the number of early comments (cost) and the predictive accuracy (gain) follows the law of diminishing marginal utility. We build the functions of these elements via curve fitting to find the appropriate number of early comments (approximately 250) that can achieve maximum gain at minimum cost.

According to the classical communication theories, known as Gate keeping and Selective Exposure, individuals tend to have selective behavior when they disseminate and receive information based on their psychological preferences. Selective behavior related to these two theories have been broadly studied separately. While, thanks to the advent of Online Social Networks (OSNs), larger-scale feedback and user information can be collected. In this paper, based on these data, We analyze the correlation among users' properties (such as age, gender, and cultural background) and analyze their selective behavior by tagging users as disseminators and/or audiences in YouTube, Flickr, and Twitter. We find that despite enormous amount of content available in OSNs, users have a comparatively small selective range and do exhibit selective behavior properties. In particular, they pay the most attention to the content published by disseminators that share similar properties, i.e., gender, age, and country. Nonetheless, we also find significant differences and commonalities among the three OSNs with respect to selective behavior. In particular, (i) the proportion and properties of disseminators, audiences, and dual-role users are quite different for the three networks, (ii) the global level of information spread in Flickr is almost two times than that in Twitter and YouTube is approximately the median one, (iii) For a given country, the global level of information spread is different for different OSNs. For a given OSN, it is different for different countries, (iv) despite ubiquitous presence of dual-role users in OSNs, most of such users are very active as either disseminators or audiences, but not both. Our findings are not only useful for understanding these two theories, but also have applications ranging from advertising and recommendation systems to developing predicting models.