Detecting Crime Related Twitter Posts using Artificial Neural Networks based Approach

• Main Authors: Sandagiri, S.P.C.W, Kumara, B.T.G.S, Kuhaneswaran, Banujan
• Format: Conference Proceeding
• Language: English
• Subjects: Artificial Neural Network; Artificial neural networks; Blogs; Crime detection; Drugs; GLoVe; Machine learning; Social networking (online); SVM; Task analysis; Training
• ISSN: 2472-7598
• DOI: 10.1109/ICTer51097.2020.9325485

Crime is defined as an act harmful not only to the individual involved but also to the community as a whole. We can identify the crime patterns and predict the crimes by detecting and analyzing the historical data. However, some crimes are unregistered and unsolved due to a lack of evidence. Thus, detecting crimes is a still challenging task. Recently, Social Networks are becoming a great environment for sharing news. Thus, we can use social media like twitter to detect crimes related activities. Because Twitter users sometimes convey messages related to his or her surrounding environment via twitter. In this paper, we proposed a machine learning approach to detect the crimes and the location of the crimes. As the first step, we fetch the twitter posts using predefined keywords relating to the crimes. Then, we constructed an Artificial Neural Network (ANN) model to classify the twitter posts. Then in the final stage, we get the geolocation and crime type. The empirical study of our prototyping system has proved the effectiveness of our proposed crime detection approach.