Criminal Event Detection and Classification in Web Documents Using ANN Classifier
J. Sheela and A. Vadivel
Department of Computer Application, National Institute of Technology, Tiruchirappalli, Tamil Nadu, India-620015
Abstract—Text mining can be described as the process of extracting particular information from within unstructured data, thereby facilitating access to potentially valuable information for use in a wide variety of fields. In this paper, we selected the crime domain to explore the hidden important information using text mining techniques. Developing an effective and intelligent system for extracting the important and hidden information from crime reports and Social Networking websites would be useful for police investigators, for accelerating the investigative process which helps in crime prediction by conducting further analysis. The proposed approach deals with automatic construction of crime related thesaurus. The proposed information extraction approach relies on computational linguistic techniques. The domain related terms and its related sentences are selected to identify patterns of interest. Further, syntactic analysis is done based on POS Tagging. Sentences Classification and clustering is done based on the sentence patterns using ANN.
Index Terms—event detection, pattern classification, detection and recognition, criminal activities, web patterns, NLP, knowledge mining
Cite: J. Sheela and A. Vadivel, "Criminal Event Detection and Classification in Web Documents Using ANN Classifier," International Journal of Signal Processing Systems, Vol. 4, No. 5, pp. 382-388, October 2016. doi: 10.18178/ijsps.4.5.382-388
Cite: J. Sheela and A. Vadivel, "Criminal Event Detection and Classification in Web Documents Using ANN Classifier," International Journal of Signal Processing Systems, Vol. 4, No. 5, pp. 382-388, October 2016. doi: 10.18178/ijsps.4.5.382-388