Iranian Journal of Information Processing & Management (Mar 2020)
Machine Indexing of Documents in the Field of Information Retrieval Using Text Mining in the RapidMiner Software
Abstract
The compatibility of classification codes and indexing terms done from a codified thesaurus with words and phrases that are automatically extracted using machine indexing. In designing an outo-indexing system, the computer completely replaces humans. The purpose of this research was to identify and extracting keywords and the subject trends of articles in the field of information retrieval and the subject's specificity of the author of each article by using the text mining and categorizing (classifying) with the help of concurrence vocabularies.The method of this research is applied and based on the CRISP model of data mining and text mining algorithms are used. The research community has 313 articles has in the field of information retrieval indexed at Noormags database. After normalizing the text of with the Virastyar software, during the text mining of the articles with the 7.1 version of the RapidMiner software, the keywords are extracted by their weight and the data are categorized using two classical classification algorithms, namely, KNN and Naïve Bayse were analyzed. In this study, the computer automatically indexed the readable machine text by using the frequency of the words with the help of the text mining tools of RapidMiner software. For this purpose, we use N-gram operators and calculate the weight of the words according to tf-idf method, Terms and key concepts and subject and specialization of author of each article is extracted in the form of 16 categories. Finally, the superiority of the KNN model In the categorization of the core subjects of the papers, this study is proving to be 85% more accurate than the Naïve bayse model. Finding the results of calculating the accuracy of the models indicate the acceptable performance of the RapidMiner software in machine indexing of texts. Indexing texts using this method can help improve the results of information retrieval and prevent false dropping of information in databases.
