@inproceedings{www2009173, booktitle = {18th International World Wide Web Conference}, month = {April}, title = {Link Based Small Sample Learning for Web Spam Detection}, author = {Guang-Gang Geng and Qiudan Li and Xinchang Zhang}, year = {2009}, pages = {1185--1185}, url = {http://www2009.eprints.org/173/}, abstract = {Robust statistical learning based web spam detection sys- tem often requires large amounts of labeled training data. However, labeled samples are more difficult, expensive and time consuming to obtain than unlabeled ones. This pa- per proposed link based semi-supervised learning algorithms to boost the performance of a classifier, which integrates the traditional Self-training with the topological dependency based link learning. The experiments with a few labeled samples on standard WEBSPAM-UK2006 benchmark showed that the algorithms are effective. } }