文章基本信息

标题：A Study of the Effects of Textual Features on Prediction of Terrorism Attacks in GTD Dataset
本地全文：下载
作者：Mohammed Abdalsalam ; Chunlin Li ; Abdelghani Dahou 等
期刊名称：Engineering Letters
印刷版ISSN：1816-093X
电子版ISSN：1816-0948
出版年度：2021
卷号：29
期号：2
页码：416-431
语种：English
出版社：Newswood Ltd
摘要：Terrorist attacks are the biggest challenges tohumanity around the world, which needs intensive efforts fromresearchers. Detecting the regularity of patterns and behaviorsof terrorism is crucial to global counter-terrorism strategies.Machine learning techniques have shown significant effectiveness in the endeavor against terrorism. Nowadays, by usinghuge detailed terrorism data, researchers can develop tools thatmay contribute to dealing with terrorism. In this paper, we aimto create a framework for terrorism attacks predicting the useof global terrorism database (GTD). The research approachassumes that textual features may affect the enhancement ofthe classifier’s ability to predict the types of terrorist attacks.To prove this hypothesis; text features are extracted andrepresented using different text representation techniques suchas Term Frequency-Inverse Document Frequency (TF-IDF),Bag of Words (Bow), and Word Embedding (W2vec). Extractedfeatures are then combined with data set features, which arecalled (key features). Nine different classifiers are employed.The results show that the combination of textual features withkey features improved the prediction accuracy significantly.
关键词：GTD; Terrorism Attack Predication; Text Classification; Machine Learning