Real-Time Effective Framework for Unstructured Data Mining

Today, the enterprise landscape faces voluminous amount of data. The information gathered from these data sources are useful for improving on product and services delivery. However, it is challenging to perform knowledge discovery in database (KDD) activities on these data sources because of its unstructured nature. Previous studies have proposed the hierarchical clustering methodology since it enhances human readability and provides clear dependency structure through topics, term and document organization. But, the methodology can be resource intensive and time consuming. In order to improve on the terms extraction process, we propose a tool called RSenter that searches through interconnected Hyperlinks and NoSQL database (specifically, CouchDB). We evaluate the tool based on search algorithms such as parallelization, random walk (or linear search), pessimistic search, and optimistic search. The tool shows high accuracy and optimality in view of the search time.