Keywords:Information Extraction, Data Dictionary, Prediction Model, Textual Database Structure, Crude Oil Market
This research demonstrates the data collection system for gathering and collecting a number of news and articles in crude oil market and presents how to analyze the trend of crude oil market by using the concept of Information Extraction and Data Dictionary, which consists of Behavior Trend and Sentimental Factor contexts. The following concepts will help analyst to predict the oil market trend faster even though the prediction process still be semi-automated. The precision rate is approximately 60 percent after comparing with the actual crude oil price due to the sample news in 30 days. In addition, this paper illustrates the prediction equation model to proof how to predict the trend of oil price and implement the model via the web application. The researchers believe that both information extraction and data dictionary could be a prospect direction to improve the prediction model of crude oil price being more automation.
The article has been published in Kasem Bundit Engineering Journal (KBEJ) is the copyright of the Kasem Bundit University. Do not bring all of the messages or republished except permission from the university.
If the article is published as an article that infringes the copyright or has the wrong content the author of article must be responsible.