Terrorism is a global threat that affects the political, economic, and social stability of many countries. The number of victims killed is based on the duration of the terrorism incident. This study uses the Residual Network (ResNet) model to classify terrorism incidents based on the duration of the incident (less than 24 hours and more than 24 hours) using the Global Terrorism Database (GTD) dataset. The GTD data used covers terrorism incidents from 1970 to 2017, with a total of 181,691. After preprocessing the data by converting categorical features to numeric and removing missing values, the data was divided into training, validation, and test sets with a composition of 70%, 15%, and 15%. The results show that the ResNet model is able to achieve a validation accuracy of 99.61% and a validation loss value of 0.0183. These findings show that the ResNet model is effective in classifying the duration of terrorism incidents and has the potential to be used in the development of better terrorism prevention systems.
Read full abstract