Data-driven human and bot recognition from web activity logs based on hybrid learning techniques

作     者：Marek Gajewski Olgierd Hryniewicz Agnieszka Jastrzębska Mariusz Kozakiewicz Karol Opara Jan Wojciech Owsiński Sławomir Zadrozny Tomasz Zwierzchowski Marek Gajewski;Olgierd Hryniewicz;Agnieszka Jastrzębska;Mariusz Kozakiewicz;Karol Opara;Jan Wojciech Owsiński;Slawomir Zadrożny;Tomasz Zwierzchowski

作者机构：Systems Research InstitutePolish Academy of SciencesWarsawPoland Faculty of Mathematics and Information ScienceWarsaw University of TechnologyWarsawPoland EDGE NPD Ltd.CoWarsawPoland 

出 版 物：《Digital Communications and Networks》 (数字通信与网络（英文版）)

年 卷 期：2024年第10卷第4期

页      面：1178-1188页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the ABT SHIELD(Anti-Bot and Trolls Shield)project at the Systems Research Institute,Polish Academy of Sciences,in cooperation with EDGE NPD RPMA.01.02.00-14-B448/18-00 funded by the Regional Development Fund for the development of Mazovia 

主　　题：Web logs Classification Clustering Web traffic Bots Interpretability 

摘      要：Distinguishing between web traffic generated by bots and humans is an important task in the evaluation of online marketing *** of the main challenges is related to only partial availability of the performance metrics:although some users can be unambiguously classified as bots,the correct label is uncertain in many *** calls for the use of classifiers capable of explaining their *** paper demonstrates two such mechanisms based on features carefully engineered from web *** first is a man-made rule-based *** second is a hierarchical model that first performs clustering and next classification using human-centred,interpretable *** stability of the proposed methods is analyzed and a minimal set of features that convey the classdiscriminating information is *** proposed data processing and analysis methodology are successfully applied to real-world data sets from online publishers.