How Stemming Help to Track Bugs in Bug Tracking System

In this paper we analyze theoretically how steaming help to track bugs in bug tracking system (BTS). Stemming is very important part of natural language processing (NLP). NLP is used to find bug related terms by reading line by line text summary that is given by Users, developer, and testers. The Bug Tracking System (BTS) is use to maintain bug related database with important attributes i.e. ID, Product, Component, Assignee, Status, Resolution, Summary, Changed Time and Category. The data is collected from various sources such as end users, testers and development teams. When bug is reported by bug reporters to a Bug Tracking System, the reporters required to label the bug reports as Security Bug Reports (SBR) or not i.e. Not Security Bug Reports (NSBR). It is necessary to prioritize the SBRs, to fix first then NSBRs. But, what happen when reporters misclassify the SBR as NSBR? It’s may cause serious problems to our system if we not fix SBR in specific time. So, to identifying NSBR is SBR we use text-mining of summary reports given in summary attribute with respect to considered attributes of product, component, resolution and state. So, with the help stemming we compact the terms by removing the grammatical form of the words. These compressed data term more understandable form. By this way we get best security related words. That help to find what actually our report is SBR or NSBR.