Title Of Paper:
 
 
Bm25 Ranking Algorithm Development Using Matching Concepts in Unstructured Text
Author's Name :  Masoud Ogbi , Mansour Aminilari
KeyWords:   ranking, data mining, text mining, matching concepts
Pages:  10 -17
Volume: 3
Issue: 8
Year: 2015
Abstract:
 

 

Today, with the development of database systems and the data stored in these systems, the need for a tool to allow the stored data to be processed and the information obtained from this process will be available to users. Using simple questions in databases and various tools can be regular reporting of information to users. To make conclusions about data and logical relationships among them, but when the data volume is high As a professional and experienced users that they cannot discern useful patterns among large amount of data, or if they are unable to do so, the cost of treatment is very high in terms of human and financial resources. So now, classic paradigm shift models and analysis models are based on the basic principles of progress and analysis of data directly from there. Data mining is one of the most important methods by which useful patterns in data with a minimum of operator intervention known and provides information to users and analysts are based on critical decisions to be made in organizations. BM25 algorithm of ranking algorithms is considered successful. The use of this algorithm in Persian literature and also contains a combination of Persian and Latin texts that are sometimes caused problems for some loss of precision, accuracy and the recall algorithm. In this study are offered to fix the problem and the results will be evaluated.

Full Text: