Information cascades are ubiquitous in various online social networks. Outbreak of cascades could cause huge and unexpected effects. Therefore, predicting the outbreak of cascades at early stage is of vital importance to avoid potential bad effects and take relevant actions. Existing methods either adopt regression or classification technique with exhaustive feature engineering or predict cascade dynamics via modeling the stochastic process of cascades using a hard-coded diffusion–reaction function. One salient issue of these methods is that these methods heavily depend on human-defined knowledge, features or functions. In this paper, we propose to use recurrent neural network with long short-term memory to directly learn sequential patterns from information cascades, working in a fully data-driven manner. With the learned sequential patterns, the outbreak of cascade could be accurately predicted. Extensive experiments on both Twitter and Sina Weibo datasets demonstrate that our method significantly outperforms state-of-the-art methods at the prediction of cascade outbreaks.

Outbreak prediction in social networks is a part of popularity dynamic analysis of social networks,and it is an active research topic in the domain of social computing.This study proposes a social messages outbreak prediction model based on recurrent neural network (SMOP) by modeling the message propagation process.Compared with the traditional models on machine learning,SMOP directly models the arrival process of message without the need of tedious feature engineering in traditional methods.When it comes to point process models,SMOP is able to automatically learn the rate functions of propagation process,making it adaptable to a variety of scenarios.Moreover,time vector and user vector,which contain the periodicity of time and the user profile,are used as input to improve the performance of outbreak prediction.Experimental results on real word data sets such as Twitter and Sina Weibo show that SMOP has excellent data adaptability,and it is able to predict whether a message would outbreak with higher F1 score in the beginning of the message spread (within 0.5h).

Discovering influential spreaders is a valuable task in social networks ,especially for the popularity prediction and analysis of online contents on microblogs ,such as Twitter and Weibo .The k-shell decomposition (k-core) ,which identifies influential spreaders located in the core of a network , attracts more attention due to its simpleness and effectiveness compared with various related methods , such as indegree ,betweenness centrality and PageRank .However ,k-shell method only considers the factor of the network position of nodes and ignores the impacts of the content itself in information diffusion .The content itself plays an important role in the process of diffusion .For example ,ones just retweet their interested tweets in microblogs .The spread ability of users depends not only on topology structures but also on the published contents ,and therefore a unified model considering the two aspects simultaneously is proposed to model users' influence .Specifically ,the topics hidden in user generated contents (UGC) are exploited to model the users' propagation probability and a topic-sensitive k-shell (tsk-shell ) decomposition algorithm is proposed . Experimental studies on a real Twitter dataset show that the tsk-shell outperforms traditional k-shell by 40% on average in the task of finding top k influential users ,which proves the effectiveness of the tsk-shell algorithm .

新兴话题检测是社交网络研究的热点问题之一。在线社交网络特别是微博的开放性,给话题的流行和爆发提供了前所未有的便利条件。新兴话题是即将流行或爆发的话题,往往伴随着重大的事件或新闻的发生,会产生重大的社会影响,如何在早期识别此类话题,是新兴话题检测研究的主要内容。该文回顾了近年来在新兴话题检测方面的主要进展,分析了新兴话题检测领域面临的挑战,阐述了相关的概念、方法和理论,重点从内容突发特征和信息传播模型两个方面对影响新兴话题检测的方法进行了分析和讨论,并对新兴话题检测的前景做了展望。

Regular expression matching is essential for network security applications.In this paper a smi-SCT State transition Compressed Table of sparse matrix index algorithm was proposed.Firstly a sparse matrix and index table were introduced into Deterministic Finite Automaton DFA with a general create method of them.Then combined with the smi-SCT with alphabet compression table algorithm an optimization strategy of the algorithm was given.At last proved the compression effect of smi-SCT and gave the applicable scope of smi-SCT according to the experimental results on compression effects.

Regular expression matching is an important application in the area of network security. In this paper, we analyse the limitation of the existing methods and show the classification of counting constraints patterns. We then present a new representation for deterministic finite automata, called Bitmap Shift Finite Automata (Bs-FA), which introduces condition function and bitmap structure. Bs-FA handles counting constraints patterns effectively and considerably reduces memory space requirement of states by evaluating this method on signature sets used in Snort. Overall, for all signature sets and compression methods evaluated of counting constraints patterns, Bs-FA offers the best memory reduction.