Abstract
Generally, keyword recurrences change over certain periods of time. Traditional approaches estimated classes (increasing, relatively constant and decreasing) that indicate keywords' attribute 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 languages 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 0.811, 0.917, and 0.897 which indicates effectiveness of our method.