An approach based on combination of Features for automatic news retrieval

Abstract

1 Department of Computer Engineering, Yadegar-e-Imam Khomeini (RAH) Shahr-e-Rey Branch, Islamic Azad University, Tehran, Iran 2 Department of Computer Engineering, Karaj Branch, Islamic Azad University, Karaj, Iran (Received October 15 2019, accepted December 26 2019) Nowadays, according to the increasingly increasing information, the importance of its presentation is also increasing. The internet has become one of the main sources of information for users and their favorite topics. \u00a0It \u00a0also \u00a0provides \u00a0access \u00a0to \u00a0more \u00a0information. \u00a0Understanding \u00a0this \u00a0information \u00a0is \u00a0very \u00a0important \u00a0for providing the best set of information resources for users. Content providers now need a precise and efficient way to retrieve news with the least human help. Data mining has led to the emergence of new methods for detecting related and unrelated documents. Although the conceptual relationship between documents may be negligible, \u00a0it \u00a0is \u00a0important \u00a0to provide \u00a0useful \u00a0information \u00a0and \u00a0relevant \u00a0content \u00a0to users. \u00a0In \u00a0this \u00a0paper, \u00a0a \u00a0new approach based on the Combination of Features (CoF) for information retrieval operations is introduced. Along with introducing this new approach, we proposed a dataset by identifying the most commonly used keywords in documents and using the most appropriate documents to help them with the abundance of vocabulary. Then, using the proposed approach, techniques of text categorization, evaluation criteria and ranking algorithms, the data were analyzed and examined. The evaluation results show that using the combination of features approach improves the quality and effects on efficient ranking.