Identifying hidden nodes in social networks is a critical issue in security-related applications. In contrast to the conventional node classification on graphs with all nodes being observable, it is more challenging to classify the hidden nodes that are unobservable during the training process, also known as the “inductive learning” in previous research. Existing approaches for inductive node classification mainly adopt graph neural network models to learn node representations. Although these methods are advantageous to modeling the topology of graph-structured data, they rely heavily on node features which may vary significantly in different specific application scenarios. In addition, the inherently changeable graph structure induced by hidden nodes may cause the over-fitting problem. To address the above issues and boost the performances of hidden node classification, we propose a deep generative model based on variational auto-encoders. Specifically, we design a novel graph neural network to aggregate the multi-hop neighbor information of each node. Meanwhile, to better utilize the graph structure information as a supplement to node features, we consider the heterogeneous node influences and introduce a gated attention mechanism using node degrees. Moreover, our proposed model can be trained by minibatches and thus is applicable to large social networks. We conduct experiments on four real-world datasets, and verify the effectiveness of our method for hidden graph node classification.

The massive spread of false information has brought about severe security-related problems to individuals and society. To debunk misinformation automatically, fact checking has become an important task that aims at retrieving evidence from external sources to verify the truthfulness of a given claim. As knowledge graph (KG) is a classic external source for retrieving relevant evidence. Previous methods typically check a claim by making inferences over it. Entity category information can be utilized to strengthen both the learning and verification process. However, this information was largely ignored in previous research. To make better use of the category information, in this paper, we propose a category-based framework for improving the performance of fact checking with KGs. We first learn prototypes for each category as their representatives, and then propose a prototype-based learning technique for effectively modeling the entity dependency in KG. We further develop a prototype matching technique to explore the category-level relations between head and tail entities for more robust verification. Experimental results on two benchmark datasets and a real-world dataset show that our framework can significantly improve the reasoning abilities of KG reasoning methods on Fact Checking task.

Social emotion refers to the emotion evoked to the reader by a textual document. Compared to classical sentiment analysis conducted from the author's perspective, emotion analysis from the reader's perspective (i.e. social emotion mining) is an important task in web-based social media analytics, and particularly meaningful for security related applications. Mining the causes of social emotions, i.e. Social Emotion Cause Extraction (SECE), is a new challenging task in social emotion mining, which can help better explain the elicited social emotions in text. In this paper, we propose the SECE task for the first time, and construct a new SECE dataset to support our study. We develop the first computational method for this new task, and conduct experimental studies to evaluate the effectiveness of our proposed method based on the dataset we construct.

News media has become a prevalent information spreading platform, where news sites can reprint news from other sites. To better understand the mechanism of news propagation, it is necessary to model reprint behavior and predict whether a news site will reprint a piece of news. Most existing works in news reprint analysis focus on analyzing the semantic of news content, little work has been done on integrating reprint relationship among sites and news content for reprint prediction from the perspective of sites. The challenge of improving prediction performance lies in how to effectively incorporate these two kinds of information to learn a more comprehensive reprint behavior model. In this paper, we propose an Integrated Neural Reprint Prediction (INRP) model that considers both reprint relationship and news content. It models the reprint relationships as a directed weighted graph and maps it into a latent space to learn sites representations. During news content modeling process, sites representations are embedded as attention guidance to build up more site-specific content representations. Finally, sites and news representations are jointly modeled to predict whether a piece of news will be reprinted by a site. We empirically evaluate the performance of the proposed model on a real world dataset. Experimental results show that taking both the reprint relationship and news content information into consideration could allow us make more accurate analysis of reprint patterns. The mined patterns could serve as a feedback channel for both corporations and management departments.

Cognitive dissonance is a ubiquitous phenomenon which can be applied in various fields potentially. In this paper, we study cognitive dissonance through empirical analysis on social media platforms. Our study focuses on a recent “reversal event” - a topic or event experiencing a reversed development trend because of the new facts. Through statistical analysis and semantic analysis based methods, we found that (1) after the event is revised, the performance of the original followers were abnormal, which is consistent with the existence of cognitive dissonance; (2) the followers' attitude afterwards usually tended to maintain their previous behaviors. This research provides a primary building block towards the mental inference based behavior prediction for social media users, which is of great value for security related research issues.

With the rapid development and wide application of new media, predicting the popularity of policy information on new media is of great significance for understanding and managing public opinion. However, the complexity of the diffusion patterns of policy information has brought great challenges for predicting the popularity of such information. Inspired by the methods of popularity prediction for short text information from social networks, we propose a framework for the popularity prediction of policy information. In our framework, first, the features of policy information are extracted from three dimensions: contextual information, social information and textual information. Then, effective features, such as the topic distribution, popularity competition intensity and hot information relevance, are identified by empirical analysis. Finally, the effective features are input into the prediction model to predict the popularity of policy information. We evaluate the performance of our proposed framework using a real-world dataset and the experimental results show that the framework can efficiently predict the popularity of policy information and that the features that we used are effective in improving the accuracy of policy information popularity prediction. The accurate prediction result could benefit policy makers, allowing them to make better decisions, understand and manage public opinion.

Social media, such as Facebook and Twitter, has become one of the most important channels for information dissemination. However, these social media platforms are often misused to spread rumors, which has brought about severe social problems, and consequently, there are urgent needs for automatic rumor detection techniques. Existing work on rumor detection concentrates more on the utilization of textual features, but diffusion structure itself can provide critical propagating information in identifying rumors. Previous works which have considered structural information, only utilize limited propagation structures. Moreover, few related research has considered the dynamic evolution of diffusion structures. To address these issues, in this paper, we propose a Neural Model using Dynamic Propagation Structures (NM-DPS) for rumor detection in social media. Firstly, we propose a partition approach to model the dynamic evolution of propagation structure and then use temporal attention based neural model to learn a representation for the dynamic structure. Finally, we fuse the structure representation and content features into a unified framework for effective rumor detection. Experimental results on two real-world social media datasets demonstrate the salience of dynamic propagation structure information and the effectiveness of our proposed method in capturing the dynamic structure.

Emotion cause extraction aims at automatically identifying cause clauses for a certain emotion expressed in a document. It is an important task in emotion analysis since it helps form a deeper understanding of emotion text. Detecting potential causes of user emotion in online contents is beneficial to public opinion monitoring, government decision-making, and other security-related applications. Existing studies treat this task as a binary clause-level classification problem, which considers each clause separately and omits the context information of clauses. Moreover, previous work only models emotion-dependent linguistic representations of clauses but ignores emotion-independent features in clauses including cause indicators. To address the above two issues, we formalize this task as a sequence labeling problem and propose the COntext-aware Multi-View attention networks (COMV) for emotion cause extraction. Our proposed model integrates context information and learns multi-view clause representations. Experimental results show that our model outperforms existing state-of-the-art methods.

News diffusion prediction aims to predict a sequence of news sites which will quote a particular piece of news. Most of previous propagation models make efforts to estimate propagation probabilities along observed links and ignore the characteristics of news diffusion processes, and they fail to capture the implicit relationships between news sites. In this paper, we propose an algorithm to model the news diffusion processes in a continuous space and take the attributes of news into account. Experiments performed on a real-world news dataset show that our model can take advantage of news’ attributes and predict news diffusion accurately.

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.

With the rapid growth of Web 2.0, social media has become a prevalent information sharing and spreading platform, where users can retweet interesting messages. To better understand the propagation mechanism for information diffusion, it is necessary to model the user retweeting behavior and predict future retweets. Some existing work in retweeting prediction based on matrix factorization focuses on using user-message interaction information, user information and social influence information, etc. The challenge of improving prediction performance is how to jointly perform deep representation of these information to solve the sparsity problem and then learn a more comprehensive retweeting behavior model. Inspired by word2vec and co-factor matrix factorization model, this paper proposes a hybrid model, called HCFMF, for learning users' retweeting behavior, it first computes the message content similarity by considering the message co-occurrence, the author information and word2vec based low-dimensional representation of content, then, jointly decomposes the user-message matrix and message-message similarity matrix based on a co-factorization model. We empirically evaluate the performance of the proposed model on real world weibo datasets. Experimental results show that taking the dense representation of author and content information into consideration could allow us make more accurate analysis of users' retweeting patterns. The mined patterns could serve as a feedback channel for both consumers and management departments.

Monitoring the evolution phases of real-time event including occurrence, development, climax, decline and ending is crucial for management department to intuitively and comprehensively understand the event and then make better decisions. However, there have been very few studies on performing phase evolution analysis of event using the number of posts at the specific time unit. The challenge of this problem is how to identify temporal pattern and mine topic of different phases automatically. In this paper, we propose a unified phase evolution mining model, it firstly identifies the temporal patterns of phases based on k-means and empirical rules, then, burst detection algorithm is adopted to discover peak interval of all phases, finally, we use a summarization technique TextRank to extract keywords from contents to summarize the topics in each phase. In addition, we perform experiments on two real-world datasets collected from different social media platform to understand the event evolution in a more comprehensive way. Experimental results show the characteristics of event evolution on different social media platforms and verify the efficacy of the proposed model.

With the rapid growth of Web 2.0, social media has become a prevalent information sharing and seeking channel for health surveillance, in which users form interactive networks by posting and replying messages, providing and rating reviews, attending multiple discussion boards on health-related topics. Users' behaviors in these interactive networks reflect users' multiple interests. To provide better information service for users, it is necessary to analyze the user interactions and predict users' multi-interests. Most existing work in predicting users' multi-interests based on multi label network classification focuses on using approximate inference methods to leverage the dependency information to improve classification results. Inspired by deep learning techniques, DEEPWALK learns label independent latent representations of vertices in a network using local information obtained from truncated random walks, which provides an efficient way for predicting users multi-interests from user interactions. In this paper, we develop a user's multi-interests prediction model based on DEEPWALK, weight information of user interactions is considered when modeling a stream of short constrained random walks and SkipGram is employed to generate more accurate representations of user vertices, which help identify users' interests. Experimental results on two real world health-related datasets show the efficacy of the proposed model.

Illicit trade in tobacco products (ITTP) would severely disrupt the market order, greatly threaten citizen's health, and damage the interests of the nation and the consumers, which has attracted great attention of tobacco monopoly administration. Quick and correct detection of the changes and the drivers of ITTP activity would be very significant to the surveillance, tracing, early warning, prediction, prevention and control of the illicit tobacco trade, which are very important challenges for tobacco monopoly administrations in China. In this paper, we introduce spatial-temporal analysis techniques into detecting the spatial-temporal patterns and drivers of ITTP based on the dataset provided by tobacco monopoly administration of Changsha county in Hunan province, China. The results suggested that ITTP in the county mostly occurred along the downtown-county borders, or nearby the toll stations located on the highway, logistics and freight distribution center and the junction of neighboring areas. Positive correlations were found between illegal rate and population density, the number of kindergartens and nursery schools, proximity to the borders, the number of the pupils and the middle school students, which was consistent with the previous study and social etiquette. This study could provide important intelligence and clues for the decision makers and make sure that the resources should be allocated as effectively as possible.

Review rating prediction is of much importance for sentiment analysis and business intelligence. Existing methods work well when aspect-opinion pairs can be accurately extracted from review texts and aspect ratings are complete. The challenges of improving prediction accuracy are how to capture the semantics of review content and how to fill in the missing values of aspect ratings. In this paper, we propose a novel review rating prediction method, which improves the prediction accuracy by capturing deep semantics of review content and alleviating data missing problem of aspect ratings. The method firstly learns the latent vector representation of review content using skip-thought vectors, a state-of-the-art deep learning method, then, the missing values of aspect ratings are filled in based on users? history reviewing behaviors, finally, a novel optimization framework is proposed to predict the review rating. Experimental results on two real-world datasets demonstrate the efficacy of the proposed method.

Emotion entrainment accounts for the rhythmic convergence of human emotions through social interactions. This phenomenon abounds in various disciplines, i.e. effervescency in soccer games, anger proliferation in violence incidents, or anxiety diffusion in disasters. Although emotion entrainment is highly relevant to the quality of human daily life, the principles underpinning this phenomenon is still unclear. Previous dynamic models try to explain entrainment phenomenon by assuming symmetrical coupling among identical individuals. Yet this assumption clearly does not hold in real-world human interactions. As such, we propose an alternative model that captures asymmetric relationships. In depicting the coupling mechanism, the effect of social influence is also encoded. Experimental results on two emergent social events suggest that the proposed model characterizes emotion trends with high accuracy. Also, we explain the emotion dynamics by analyzing the reconstructed entrainment matrix. Our work may present practical implications for those who want to guide or regulate the emotion evolution in emergency events discussed online.

Weibo has become an important information sharing platform in our daily life in China. Many applications utilize Weibo data to analyze hot topic and opinion evolution patterns to gain insights into user behavior. However, various spam messages degrade the performance of these applications and thus are essential to be filtered. In this paper, we propose a unified spam detection approach, which utilizes external knowledge sources to expand keywords features and applies an ensemble under-sampling based strategy to handle the class-imbalance problem. The experimental results show the effectiveness and robustness of our approach in Weibo data.

Action knowledge is an important type of behavioral knowledge and of vital importance to many applications in social computing, especially in behavior modeling, analysis and prediction. In this paper, we present a computational method to action knowledge extraction from online media. Our approach is based on mutual bootstrapping and combined with knowledge reasoning. Compared with the related work, our approach can acquire more types of action knowledge, and needs much less human labor. We evaluate the performance of our method using the Web textual data from security informatics domain. The experimental results show the effectiveness of our proposed method.

Extracting emotions from online reviews is crucial to many security-related applications as well as applications in other domains. Traditional approaches to emotion extraction have mainly focused on mining the polarities of opinions or using annotated data to extract emotion types. Emotion theories, which identify the underlying cognitive structure and emotional dimensions that are key to generate emotions, have almost been totally ignored in previous work. To facilitate the automatic extraction of emotions from textual data, in this paper, we propose an emotion model based approach to emotion extraction from online reviews. Informed by the widely used OCC emotion model, we employ a statistical method to extract emotion words with their dimension values from texts, and implement OCC model to obtain emotions based on the emotion-dimension dictionary. We conduct an empirical study using security-related news reviews. The experimental results demonstrate the effectiveness of our proposed approach.

Click fraud (CF) has become a serious problem in the online advertising, making the anti-CF issue quite important. In this paper, we analyze the effects of the price determination model on the CF situations in online advertising. Our theoretical results show that the flat-rate model can induce more click frauds than the real-time-bidding model. Our finding is validated with a real advertising dataset.

Query by humming (QBH) is an interactive tool for retrieving favored songs from a large database of known media via acoustic input. In this task, common method for measuring similarity between query and candidate is either by symbolic notation distance or by framed based dynamic programming. However, the former has disadvantage of error-prone to the noted symbolic feature extraction stage, while the latter is time-consuming. It has been proved that transportation distance has its remarkable merit in image query. However, we adopt a new structure for handling QBH, which is based on an improved version of this measure in combination with a string searching algorithm. More practically, we extend this method in random piece context, which means users can hum at any part of music piece. Experimental results are evaluated in MIREX 2007. Final 92.82% MRR has shown its significant advantages.