Automatically generated spam detection based on sentence-level topic information

Yoshihiko Suhara, Hiroyuki Toda, Shuichi Nishioka, Seiji SusakiWWW 2013 · OpenReview

Abstract

Spammers use a wide range of content generation techniques with low quality pages known as content spam to achieve their goals. We argue that content spam must be tackled using a wide range of content quality features. In this paper, we propose novel sentence-level diversity features based on the probabilistic topic model. We combine them with other content features to build a content spam classifier. Our experiments show that our method outperforms the conventional methods.
BibTeX
@inproceedings{suhara2013automatically,
  author = {Yoshihiko Suhara and Hiroyuki Toda and Shuichi Nishioka and Seiji Susaki},
  title = {{Automatically generated spam detection based on sentence-level topic information}},
  booktitle = {The Web Conference},
  year = {2013},
  url = {https://openreview.net/forum?id=HJVqHZbu-S},
}

Loading related content...

Figure