Abstract
The development of the Web has been paralleled by the emergence of harmful Web pages content such as pornography, violence, racism, etc. This emergence involved the necessity of providing filtering systems designed to secure the internet access. In this paper, we propose a violent Web content detection and filtering system called "WebAngels filter" which uses textual and structural content-based analysis. These analysis are based on a violent keyword dictionary. We focus our attention on the keyword dictionary preparation, and we demonstrate that a semi-automatic keyword dictionary can be used to improve the filtering efficiency of violent Web pages.