| Popis: |
Online data generation is increasing rapidly due to technological development. In order to handle the huge volume of data, big data methodology is used widely. Though big data can able to process huge data, it has its own issues including information storage, data management, and retrieving data. In big data, data retrieval is an issue where the method of data retrieval and implementation environment differs. Though data mining has become evolving technology, it requires an optimal retrieval mechanism to extract data from the hugerepository.Therefore, an information retrieval method which in turn should effectively perform data retrieval in terms of both speed and accuracy need to be implemented. Topic relevance mechanism is used to retrieve an appropriate document from the repository, these documents are then ranked based on user preference using pseudo-relevance feedback mechanism. And hence the accuracy of the retrieved document is improved. |
