Social-Spammer 垃圾邮件数据集

Social-Spammer-Heterogeneous 数据集是从名为 Tagged 的社交软件上收录的，它包含五百六十万的用户和八千五百万用户间的联系。数据集中的每个用户包含四个特征和一个手动输入用以鉴定是否为垃圾账号的标签分类。数据集中的每个联系则代表了两个用户间的互动，且包含一个时间戳和类别。网络中对于用户间的联系共含有七种匿名类别。该数据集最原始的任务就是基于关联与非关联的特征去鉴别垃圾账号

The Social-Spammer-Heterogeneous dataset is collected from the social media platform Tagged. It contains 5.6 million users and 85 million user-to-user connections. Each user in the dataset includes four features and a manually annotated label for spam account identification. Every connection represents an interaction between two users, and includes a timestamp and a category. There are seven anonymized categories for user-to-user connections in this network. The original core task of this dataset is to identify spam accounts based on relational and non-relational features.

搜集汇总

背景与挑战

背景概述

Social-Spammer垃圾邮件数据集源自Tagged社交软件，包含560万用户和8500万用户联系，每个用户具有四个特征和垃圾账号标签，联系则带有时间戳和七种匿名类别。该数据集的原始任务是基于关联与非关联特征来识别垃圾账号。