Account classification in online social networks with LBCA and wavelets
Account classification in online social networks with LBCA and wavelets
复制标题
DOI：
10.1016/j.ins.2015.10.039
复制
发表时间：
2016-03-01
影响因子：
8.1
通讯作者：
da Silva, Ivan Nunes
中科院分区：
文献类型：
--
作者：
Igawa, Rodrigo Augusto;Barbon, Sylvio, Jr.;da Silva, Ivan Nunes
我们开发了一种基于小波的账户分类方法，用于检测在线社交网络（OSN）上机器人的文本传播。它的主要目标是将账户模式与人类、半机械人或机器人相匹配，改进现有的自动检测欺诈的算法。该方法以适合OSN的计算代价分析关键项的分布。描述符是每个用户帐户的基于小波的特征向量，与一种新的加权方案（称为基于词典的系数衰减（LBCA））结合使用，并作为测试的分类器之一的输入：随机森林和多层感知器。使用2014年FIFA世界杯期间抓取的一组帖子进行实验，获得94至100%的准确率。(C)2015 Elsevier Inc. All rights reserved.
We developed a wavelet-based approach for account classification that detects textual dissemination by bots on an Online Social Network (OSN). Its main objective is to match account patterns with humans, cyborgs or robots, improving the existing algorithms that automatically detect frauds. With a computational cost suitable for OSNs, the proposed approach analyses the distribution of key terms. The descriptors, a wavelet-based feature vector for each user's account, work in conjunction with a new weighting scheme, called Lexicon Based Coefficient Attenuation (LBCA) and serve as inputs to one of the classifiers tested: Random Forests and Multilayer Perceptrons. Experiments were performed using a set of posts crawled during the 2014 FIFA World Cup, obtaining accuracies within the range from 94 to 100%. (C) 2015 Elsevier Inc. All rights reserved.