基于复杂网络融合产品主题的重要在线评论挖掘研究

Research of mining important online reviews based on complex network and fusion products subject

从海量的在线评论中挖掘重要评论是帮助消费者快速决策的关键。基于复杂网络理论,以评论内容为网络节点,评论间的语义相似度为链接的权重,构建在线评论网络,通过分析评论网络的全局统计数据,论证了所构建网络的合理性;依据评论网络中的社区结构特性,划分面向主题的评论网络社区;并基于PageRank网页排序算法,在结合复杂网络节点重要性评价方法的同时,结合社区属性,构建重要评论的多属性决策方法。通过仿真实验验证了该方法在全局以及局部网络的可行性和准确性。

Mining important reviews from the vast amounts of online reviews is the key to help consumers making quick decision. Based on complex network theory, this paper eonstcucted online reviews network through regarding reviews＇ content as the network nodes and the semantic similarity between reviews as the weights of link. It demonstrated the rationality of the network through the analysis of the global statistics of reviews network. And it divided the reviews network community of subject-oriented according to the community structure features of reviews network. Based on PageRank algorithms,it built a multiple-attribute decision-making method of important reviews in combination with the node importance evaluation methods of complex network and community attribute. Simulation experiments verify the feasibility and accuracy of the method in the global and local network.