Semi-Supervised Spam Detection in Twitter Stream

Most existing techniques for spam detection on Twitter aim to identify and block users who post spam tweets. In this paper, we propose a semi-supervised spam detection ((SD)-D-3) framework for spam detection at tweet-level. The proposed framework consists of two main modules: spam detection module operating in real-time mode and model update module operating in batch mode. The spam detection module consists of four lightweight detectors: 1) blacklisted domain detector to label tweets containing blacklisted URLs; 2) near-duplicate detector to label tweets that are near-duplicates of confidently prelabeled tweets; 3) reliable ham detector to label tweets that are posted by trusted users and that do not contain spammy words; and 4) multiclassifier-based detector labels the remaining tweets. The information required by the detection module is updated in batch mode based on the tweets that are labeled in the previous time window. Experiments on a large-scale data set show that the framework adaptively learns patterns of new spam activities and maintain good accuracy for spam detection in a tweet stream.