Event extraction and classification from english articles

Abstract

Today’s digital world huge number of information sources like wikis, web, blogs and other sources are creating a lot of information with several events. Basically, an event can be a situation, action or state that can be represented in natural language text in the form of happening or occurrence. Analyzing the event information finding the relation between the events is one of the crucial tasks in information retrieval. In a formal way, the event can be defined as a real-world entity that happens or occur; these are the dynamic occurrences which have causes or effects (E.g. earthquake, floods, crime, etc.). Extracting events, events fall within a timelines extraction can be applied in many of the natural language applications like text summarization, temporal question answering systems, etc. Event extraction and classification can use in other related text searches like News domains, legal documents, wikis, manuscripts, and time-based searches. In this paper, we present a methodology for event extraction in natural language text which helps in finding out the type of an event and classifies the events under specific categories. Our work aims to develop a system which would automatically identify events from articles generated over the internet. The system would not only detect the events but also tried to detect important times of the event. Finally compared the accuracy of work with several classifiers and obtained results shows good accuracy measure for Support Vectors machine (SVM).