Abstract
Social media platforms play an important role in facilitating the spread of extremism by influencing people's views, opinions, and perceptions. These platforms are increasingly used by extremist elements to spread propaganda, radicalize and attract young people. Therefore, research on the detection of extremism on social media platforms is necessary to prevent its consequences and negative consequences. It is very important to conduct a comprehensive and Comparative Study of data sets, classification methods, and screening methods using the internet extremism detection tool. The purpose of this research is to create a system for identifying ISIS and Al –Qaeda flags from images. CNN was implemented by expanding and training data sets using deep learning networks. In the course of this study, we developeda system for identifying the flags of extremist groups using images. In addition, a solution was found to increase the size of the data set. The data set contains 1,400 images, half of which are the" Al-Qaeda “flag and half are the” ISIS " flag. In addition, 2 convolutional and one fully connected layer were used to recognize the” ISIS "and" Al-Qaeda " flags. As the relevance of the work, it should be noted that the convolutional network model of CNN is trained using deep learning, that is, training based on neural networks. Novelty of the work: obtaining the highest value of the accuracy indicator using a new data set using the model classification method.The study is devoted to the study and application of deep learning methods aimed at solving the problems of identifying potentially dangerous information on the internet. With the proposed method, a 95% indicator of flag recognition from the image was achieved. The result of the proposed study can be of great help in recognizing ISIS and Al-qaeda flags and preventing terrorist activities..