Using classification and key phrase extraction for information retrieval

With the rapid development of Internet technology and the great capacities of online documents, information retrieval has become a major research topic. In this paper, a new information retrieval algorithm is proposed, which can reduce time complexity and improve accuracy using classification and key phrase extraction. Then a new criterion named ranking error is contributed to solve the problem that the traditional performance evaluation methodology can´t evaluate the ranking results of retrieved documents effectively. The experimental results indicate that the proposed algorithm outperforms vector space model and interactive retrieval based on classification in speed, accuracy and ranking error.