An Approach on Implementations Method for Arabic Keyword Tendency Using Decision Tree

Generally, Keyword recurrences change over certain periods of time. Traditional approaches estimated classes (increasing, relatively constant, and decreasing) that indicate keywords‟ attributes changes in a document over certain periods of time using a decision tree. Furthermore, all earlier approaches are based on keywords in English and French languages. Therefore, the extension of keywords to other language such as Arabic could strengthen further researches in this domain. This paper introduces new method to extract, Arabic keywords from corpora based on their recurrences changes in a document over given periods of time using a decision tree. The new approach is applied on new data set field (computer science) which makes it different to traditionally used methods. The comparison between the manually classified results and the evaluation of the decision tree results reveals that; F-measures of decreasing, relatively constant and increasing classes were 0.188, 0.789, and 0.877 which indicates effectiveness of our method. This study presented the evaluation method of Arabic keywords recurrences change based on time-changing. The approach has introduced a new method to extract Arabic keywords from corpora based on recurrences changes in a document over given periods of time using a decision tree. Three classified classes are defined using four attributes to obtain the recurrences change of Arabic keywords. A specific field (computer science) was chosen because it has recurrences reports every year, and easy to determine how Arabic keywords recurrences are affected by time-changing factors. The proposed method automatically evaluated classified classes of Arabic keywords by using DT training on past document data.