Detecting Terrorism Evidence in Text Documents

Abstract-The paper presents a model to detect terrorism evidence in textual documents. The model pre-processes domain specific documents to extract the general patterns of text associated with the domain. The model then incorporates the Conditional Random Field (CRF) model for detection of sentences containing patterns of terrorism evidence. For incorporation of CRF model, the features are selected from generalized patterns rather than the text itself. We prepared a small data set of manually tagged instances of terrorism evidence for training and testing the model. We found that the proposed model achieves better results than other models such as Hidden Markov Model or conventional CRF which are directly applied to text. The proposed model can be applied for improvement of terrorism event extraction and ontology creation systems, especially with the focus towards their effective role in Open Source Intelligence. We describe briefly the existing systems along with possible improvements with incorporation of the presented model at different levels.