Social-Spammer

社交垃圾邮件发送者异构数据集是从一个名为Tagged的社交软件中收集的，该软件包含560万用户和8500万用户之间的联系。数据集中的每个用户都包含四个功能和一个手动输入的标签分类，以识别其是否为垃圾邮件帐户。数据集中的每个链接表示两个用户之间的交互，并包含时间戳和类别。网络中用户之间的连接有七个匿名类别。该数据集最原始的任务是根据关联和非关联特征识别垃圾邮件帐户。

The Heterogeneous Social Spammer Dataset is collected from a social platform named Tagged, which has 5.6 million registered users and 85 million user-to-user connections. Each user in the dataset is associated with four features and a manually annotated label used to classify whether the user is a spam account. Each link in the dataset represents an interaction between two users, and contains a timestamp and a category. The connections between users in the network fall into seven anonymous categories. The original core task of this dataset is to identify spam accounts using both relational and non-relational features.

搜集汇总

背景与挑战

背景概述

Social-Spammer数据集是从Tagged社交软件收集的异构数据，包含560万用户和8500万用户之间的连接，每个用户具有四个特征和手动分类标签，用于识别垃圾邮件账户。数据集还包括用户交互的时间戳和七个匿名类别，核心任务是根据关联和非关联特征检测垃圾邮件账户。