中文摘要：

针对微博中的反垃圾处理问题,本文提出了基于重用检测模型的垃圾用户检测算法,该方法综合考虑了消息序列中文本相关性和时间相关性,对垃圾用户的发布行为进行建模.按照文本粒度不同,基于重用检测模型的检测算法分为语句级检测（SRD）和词项级检测（TRD）.SRD算法侧重于用户行为方式,而TRD算法侧重于垃圾消息的主题.基于真实数据集的实验表明,SRD算法在整体性能上优于TRD算法,但TRD算法具有更高的运行效率,并且检测针对性强,可发现指定类型的垃圾用户.最后,本文运用重用检测算法在垃圾用户群体检测方面做了初步尝试,实验表明基于转发关系的重用检测算法可以发现真实有效的垃圾群体用户.

英文摘要：

Tremendous increase of spam has become a serious problem.In this paper,we aim to detect microblog spammers by means of retweeting relationship.We introduce a new reuse detection model,which simultaneously incorporates text content and temporal information,to rate the intensity of spamming behaviours.We then present two spam detection algorithms based on such model.One is sentence-level detection algorithm,the other is term-level one.The sentence-level detection algorithm prefers the behaviour pattern of spammers and ignores the topic of spam messages.The term-level detection algorithm focuses the topic of spam messages and compensates for lack of sentence-level one.Finally,we evaluate our approaches on a real dataset collected from Sina microblog,the largest microblog in China.Extensive experiments show the effectiveness and efficiency of our algorithms.