Performance Comparison between Keyword-based and WQCA-based Information Retrieval System

Today, semantic logics are very important in query understanding to create successful web search engines. A user might not formalize the query when he seeks information although he knows what he wants. As a result, understanding the nature of the information that is needed behind the queries are important research problem. So, this system proposes the Web Query Classification Algorithm (WQCA) for efficient Information Retrieval (IR) system. In the WQCA process, this system firstly classifies the web queries into each characteristic (taxonomies). Then, this system extracts the domain terms from the query. By using NoSQL graph database, this system classifies each domain term into their relevant categories according to the WQCA algorithm. In the WQCA-based IR process, this system uses the classified query to find the relevant document form the document collection. Finally, this system compares the performance between keyword-based IR and WQCA-based IR to show the effectiveness of the web query classification.