Presenting a fuzzy relation to classify the Persian Web documents

摘要

Accumulation of existing web documents on the Internet from one side and rapid changes of these pages and their exponential growth made their manually organizing and retrieving almost impossible. Therefore it is necessary to have a system that can automatically put these pages into the related classes to provide their results for the applied tools to be used. Unfortunately, the classification of Persian Web documents considering their unique structure and challenges is more difficult. In this paper, the results of the classification of Persian Web documents which is obtained using a relation derived from fuzzy theory will be discussed later on. The results of this research are obtained by a survey process in which the job sequences include the construction of software, dataset of Persian Web documents and testing and assessment of the documents. The favorable results obtained from the output of this research confirm the hypothesis of the research so that the accuracy of the classification is satisfactory in compare to the average accuracy of classification in other researches.