关键词: 会话识别, 数据预处理, Web图结构, 路径补全, 数据清洗

Abstract: Data pre-processing is the basis for Web log mining, and session identification is a key step in data preprocessing, so session identification quality seriously influences Web log mining results. The paper analyzed the current session identification methods and proposed to improve session identification quality by pictures log data abandoned in data pre-processing. With reference to the expansion of Web graph structure, the improvement was made from such two aspects as page grouping rules and path completion algorithm. The method is experimentally proved to be effective to improve the session identification quality.

Key words: session identification, data pre-processing, Web graph structure, path completion, data cleaning