Co-training based semi-supervised Web spam detection

Abstract

Traditional Web spam classifiers use only labeled data (feature/label pairs) to train. Labeled spam instances, however, are very difficult, expensive, or time consuming to obtain, as they require the efforts of experienced human annotators. Meanwhile unlabeled samples are relatively easy to collect. Semi-supervised learning addresses the classification problem by using large amount of unlabeled data, together with the labeled data, to build better classifiers. This paper proposes two new semi-supervised learning algorithms to boost the performance of Web spam classifiers. The algorithms integrate the traditional co-training with the topological dependency based hyperlink learning. The proposed methods extend our previous work on self-training based semi-supervised Web spam detection. The experimental results with 100/200 labeled samples on the standard WEBSPAM-UK2006 benchmark showed that the algorithms are effective.