A method for the automatic extraction of keywords in legislative documents using statistical, semantic, and clustering relationships

Using smart methods for the automatic generation of keywords in legislative documents has attracted the attention of many researchers over the past few decades. With the increasing development of legislative documents and the large volume of unstructured texts, the need for rapid access to these documents has become more significant. Extracting the keywords in legislative documents will accelerate the legislative process and reduce costs. The present study attemptes to extract meaningful keywords from texts by using the thesaurus, which has a structured system to improve the classication of legislative documents. In this method, the semantic relationships in the thesaurus and document clustering were used and the statistical features of different words were calculated to extract keywords. After pre-processing the texts, first the keywords in the text are selected using statistical methods. Then, the phrases derived from the keywords are extracted using semantic terms in the thesaurus. After that, a numerical weight is assigned to each word to determine the relative importance of the words and indicate the effect of the word in relation to the text and compared to other words. Finally, the final keywords are selected using the relationships in the thesaurus and clustering methods. The results of testing various texts from the Parliament of Iran and the Deputy for Presidential Laws indicate the high accuracy of the proposed method in meaningful Keywords extraction.