Research on Network Chinese Pornography Characteristic and Corresponding Filtering System's Model
Yuzhong Peng · 2010
At present,the internet pornographic text is in varied forms and changeful, although it is prohibited ever. It severely harms people's mental and physical health development and social stability. There are IP-based,keyword-based and intelligent content analysis filtering system against it today. But they are difficult to deal with manifestations of diversity, changeful, and increasingly concealed porn. In this paper, a in-depth research has done for the appeared characteristics of such undesirable information on our statistical analysis. And based on this characteristics, a new text pre-processing algorithm PA-PTCI is proposed, and a effective model combined with content filtering technology to the current text information filtering pornography problem is designed. The experimental result shows the PA-PTCI algorithm and the model of Chinese pornography text filtering are quite effective.