Predicting the popularity of content is important for both host and users social media sites. The challenge this problem comes from inequality content. Existing methods prediction are mainly based on quality content, interface site to highlight contents, collective behavior users. However, little attention paid structural characteristics networks spanned by early adopters, i.e., who view or forward in stage dissemination. In paper, taking Sina Weibo as a case, we empirically study whether...

The ability to model and predict the popularity dynamics of individual user generated items on online media has important implications in a wide range areas. In this paper, we propose probabilistic using Self-Excited Hawkes Process (SEHP) characterize process through which microblogs gain their popularity. This explicitly captures triggering effect each forwarding, distinguishing itself from reinforced Poisson based where all previous forwardings are simply aggregated as single effect. We...

Cumulative effect in social contagion underlies many studies on the spread of innovation, behavior, and influence. However, few large-scale empirical are conducted to validate existence cumulative information diffusion networks. In this paper, using population-scale dataset from largest Chinese microblogging website, we conduct a comprehensive study diffusion. We base our network message, where nodes involved users links characterize forwarding relationship among them. find that multiple...

Modeling and predicting the popularity dynamics of individual user generated items on online social networks has important implications in a wide range areas. The challenge this problem comes from inequality content numerous complex factors. Existing works mainly focus exploring relevant factors for prediction fitting time series into certain class functions, while ignoring underlying arrival process attentions. Also, exogenous effect activity variation platform been neglected. In paper, we...

Predicting the popularity of content is important for both host and users social media sites. The challenge this problem comes from inequality con- tent. Existing methods prediction are mainly based on quality content, interface site to highlight contents, collective behavior user- s. However, little attention paid structural charac- teristics networks spanned by early adopters, i.e., who view or forward in stage dissemination. In paper, taking Sina Weibo as a case, we empirically study...

The subject of collective attention is in the center this era information explosion. It thus great interest to understand fundamental mechanism underlying large populations within a complex evolving system. Moreover, an ability predict dynamic process for individual items has important implications array areas. In report, we propose generative probabilistic model using self-excited Hawkes with survival theory and through which gain their attentions. This explicitly captures three key...

Community search is a personalized community discovery problem aimed at finding densely-connected subgraphs containing the query vertex. In particular, for communities with high-importance vertices has recently received great deal of attention. However, existing works mainly focus on conventional homogeneous networks where are same type, but not applicable to heterogeneous information (HINs) composed multi-typed and different semantic relations, such as bibliographic networks. this paper, we...

Effectively predicting the future popularity of online content has important implications in a wide range areas, including advertising, user recommendation, and fake news detection. Existing approaches mainly consider prediction task via path modeling or discrete graph modeling. However, most them heavily exploit underlying diffusion structural sequential information, while ignoring temporal evolution information among different snapshots cascades. In this paper, we propose learning...

Micro-blogging systems have become one of the most important ways for information sharing. Network structure and users' interactions such as forwarding behaviors aroused considerable research attention, while mention, a key feature in micro-blogging platforms which can improve visibility message direct it to particular user beyond underlying social structure, is seldom studied previous works. In this paper, we empirically study mention effect diffusion, using dataset from population-scale...

In order to conveniently classify, retrieve, and synthesize human motion, motion capture (MoCap) data need be properly segmented into distinct behaviors. this paper, we propose a novel automated segmentation method based on posture histograms in sliding window. Firstly, set of new features are proposed defined construct the histogram, which is compact representation behavioral features. Then, by executing window, especially behavior analyzed subsequence level reduce noise sensitivity. We...

The ability to model and predict the popularity dynamics of individual user generated items on online media has important implications in a wide range areas. In this paper, we propose probabilistic using Self-Excited Hawkes Process(SEHP) characterize process through which microblogs gain their popularity. This explicitly captures triggering effect each forwarding, distinguishing itself from reinforced Poisson based where all previous forwardings are simply aggregated as single effect. We...

Follow-ship network among users underlies the diffusion dynamics of messages on online social networks. Generally, structure underlying determines visibility and process. In this paper, we study forwarding behavior individuals, taking Sina Weibo as an example. We investigate multiple exposures in information "forwarding whom" problem associated with exposures. Finally, model predict combining structural, temporal, historical, content features. Experimental results demonstrate that our method...

Graphs are the universal data structures for representing relationships between interconnected objects. They ubiquitous in a variety of disciplines and domains ranging from computer science, social economics, medicine, to bioinformatics. In Recent years, extensive studies have been conducted on graph analysis techniques. One most fundamental challenges analyzing graphs is effectively graphs, which largely determines performance many follow-up tasks. This workshop aims provide forum industry...