Text Summarization for Oil and Gas News Article

Information is increasing in numbers; companies are overloaded with information until they may lost track in getting the intended information. It is time consuming to scan through each of the lengthy document; moreover a shorter version of the document which contains only the gist information is more favourable for most information seekers. Therefore, in this paper, we implement a text summarization system which is able to produce summary that contains gist information of oil and gas news articles. The resulted summary is intended to provide important information for oil and gas company to monitor their competitor’s behaviour in order to help them to formulate their business strategy. The system integrated statistical approach with three underlies concept: keyword occurrences, title of the news article and location of the sentence. The generated summaries were compared with human generated summary from an oil and gas company. Precision and recall ratio are used to evaluate the accuracy of the generated summary. Based on the experimental results, the system is able to produce an effective summary with the average recall value of 83% at the compression rate of 25%.