Text mining: Finding right documents from large collection of unstructured documents

摘要

In our day to day life we come across unstructured data in many forms. These include books journals, audio / video files and unstructured text such as emails, web pages and documents. And these data can be a vital source in order to make informed decisions. For example in any company there is a set of people who can be identified as the paramount from among its workforce. Identifying what is common among them and identifying others like them would undoubtedly improve the output of the company. This is the basis on which this research was carried out. The central aspect of the research was to use text mining techniques to mine the data in a set of documents and identify what are the common characteristics among them and then to identify other documents which contains these characteristics.