Sub-graph mining-based credit speculation and malicious evaluation identification method

The invention provides a sub-graph mining-based credit speculation and malicious evaluation identification method. The method is characterized by comprising the following steps of classifying commodity evaluations into positive evaluations and negative evaluations; establishing half binary classification networks of commodities; and analyzing the half binary classification networks. Based on online commodity evaluations, the half binary classification networks are established based on specific relationships among the commodities in a massive evaluation data set, and credit speculation and malicious evaluation identification is realized through network statistical analysis and sub-graph mining. The scheme has practical significance and application values for normalizing normal operation ofe-commerce platforms, promoting fair competition of the commodities, providing correct shopping guidance for consumers and the like. 本发明提供了种基于子图挖掘的信用炒作与恶意评价识别方法，其特征在于，包括以下步骤：将对商品的评价划分为好评及差评；建立每个商品的半二类网络；对半二类网络进行分析。本发明基于在线商品评价