复杂条件下的社区搜索方法

Approaches to Community Search Under Complex Conditions

社区搜索旨在寻找包含给定节点集的社区,能够快速获取个性化的社区信息.针对现有社区搜索算法难以满足复杂搜索条件的现状,提出条件社区搜索这一新问题.解决该问题有助于对社交网络进行智能分析,在复杂搜索条件下为用户提供更好的社区结果.首先,基于布尔表达式,给出条件社区搜索问题的形式化定义,可有效表达给定节点不能出现在社区内以及给定节点中至少有一个出现在社区内的要求.接着,提出解决条件社区搜索问题的通用框架,包括对搜索条件进行简化、根据简化后的搜索条件进行多次单项条件社区搜索、合并各单项条件社区搜索的结果等主要步骤.同时,提出"社区搜索+过滤"的方法和给点加权的方法来进行单项条件社区搜索.最后,真实数据集上的大量实验结果表明所提方法的正确性和有效性.

Community search aims to find out communities containing a given set of nodes and get personalized community information quickly. Since traditional community search algorithms can hardly meet the needs under complex conditions, a new problem called conditional community search is proposed. Solving the problem helps to analyze social networks intelligently and provides users with better community results under complex search conditions. First, based on Boolean expressions, the formal definition of conditional community search problem is given, which can effectively express the requirement that a given node cannot exist in the community and at least one of the given nodes occurs in the community. Then, a general framework is proposed to solve the problem of conditional community search, including simplifying search conditions, conducting multiple singleconditional community searches according to simplified search conditions, and combining the results of singleconditional community searches. At the same time, a community search plus filtering method and a node weighting based method are proposed to carry out the singleconditional community search. Finally, extensive experimental results conducted on real-world datasets show the correctness andeffectiveness of the proposed methods.