YouTube Spam Comments Detection Using Artificial Neural Network

摘要

YouTube is considered as one of the most popular video sharing websites that is growing very fast. Because of its popularity, it attracts different types of spammers who publish unwanted spam videos and comments. Spam comment can be defined as the comment that is not relevant to the specific content of a web page. In general, spam comments could be used to publish messages for online marketing, believes of religious, political ideas and links to spam websites that harm the computer of the user. This study presents a YouTube spam comment detection model using a fully connected feed forward neural network. The dataset used to build the model has been obtained from the UCI machine learning repository. A comparison between the ANN Model's results and the results achieved by Alberto is presented and it has been found that the ANN Model is better than most of the models used by Alberto.