Web病毒式营销核心群体挖掘与推荐策略

发布时间：2018-03-01 18:14

本文关键词： 病毒式营销核心群体影响度网络影响集可推荐度　出处：《计算机应用研究》2013年10期 　论文类型：期刊论文

【摘要】：Web病毒式营销已经成为电子商务领域中的重要营销策略,核心群体在其中发挥着重要的作用。为了挖掘核心群体并对其进行商品推荐,在Web客户信任网络(customer trust network,CTN)的基础上考虑了信任度、评价分数以及推荐次数等因素定义了影响度的概念,提出了以影响度为基础的节点网络影响集的构建方法以及基于网络影响集的核心群体挖掘算法MCGNIS(mining core group based on network-influence set),并以挖掘出的核心群体为对象建立了基于网络影响集的推荐模型RCGNIS(recommending model for core group based on network-influence set),设计了相应的推荐算法来计算商品对核心群体的可推荐度。实验证明,以节点网络影响集为基础挖掘出的核心群体在Web客户信任网络中具有较高的网络覆盖率(network-coverage,NC),推荐模型RCGNIS具有很好的推荐准确性,同时又保持了推荐的多样性。
[Abstract]:Web viral marketing has become an important marketing strategy in the field of electronic commerce, in which core groups play an important role. On the basis of Web customer trust Network (CTN), the concept of influence degree is defined by taking into account the factors such as trust degree, evaluation score and the number of recommendations. In this paper, the method of constructing the influence set of node network based on the degree of influence and the algorithm of MCGNIS(mining core group based on network-influence set based on the network influence set are proposed, and the network influence based on the core group is established. RCGNIS(recommending model for core group based on network-influence setters, a recommendation algorithm is designed to calculate the degree of recommendation to the core population. The core group mined on the basis of the node network influence set has high network coverage in the Web customer trust network. The recommended model RCGNIS has good recommendation accuracy while maintaining the diversity of recommendation.
【作者单位】：沈阳航空航天大学计算机学院;
【基金】：辽宁省自然科学基金资助项目(2011020172)
【分类号】：TP393.09

【参考文献】