Developing Indonesian corpus of pornography using simple NLP-text mining (NTM) approach to support government anti-pornography program
Miftah Andriansyah, Imam Purwanto, Muhammad Subali, Antonius Irianto Sukowati, Marshal Samos, Ali Akbar · 2017
The world of information technology and telecommunication advanced with the presence of the development the internet. With the emergence of the internet, pornography is easily obtained. Pornography in Indonesia is considered illegal because contrary to laws prevailing in Indonesia. Pornography also having the impact on bad at society under the age of one of them is how many children under age already have sexual intercourse. Approach done is taking the title from / content video pornography that is on a web page an (URL). Methods used namely semiautomatic where this method uses the method of manual and automatic and used K-Nearest Neighbor algorithm. K-Nearest Neighbor algorithm is one the algorithm can be utilized for implementation classification. With K-Nearest Neighbor algorithm can classify data that belongs to a porno or not. Tools used is web corp and programming PHP language. The manufacture of limitation from corpus this is build corpus pornography Indonesian language and data taken to object research site is 10 pornography who can access via smartphone.