微博垃圾评论检测与预处理技术

针对发表在微博上评论信息的特点，尤其是那些广大网民用户不愿看到的垃圾评论信息进行了深入研究．归纳了网络上垃圾评论的存在形式和类型，将垃圾评论分为社会网络垃圾评论和普通垃圾评论．为了有效地检测与过滤微博中评论垃圾，提出了一种微博垃圾评论数据预处理的过程和方法，将预处理后的评论信息作为分类和检测的基础．

Detection and Pretreatment Technology About Microblog Comment Spam

Based on the characteristics of the information in the Microblog comment, the comment spam information which interret users are not willing to read is studied in details. The existing forms and types of network comment spam are summarized. The comment spam is divided into social networking spam and spam comments. In order to effectively detect and filter the Microblog comment spam, the procedure and method of pretreatment Microblog comment spam data are proposed,on the basis of classification and detection.