DOCUMENT CLASSIFICATION USING MACHINE LEARNING TECHNIQUES

Abstract

Automated classification of text documents into their meaningful classes has always been 
considered as a vital method to manage and process a vast amount of documents in digital forms that are 
widespread and continuously increasing. This kind of web information, popularly known as the 
digital/electronic information is in the form of documents, conference material, publications, journals, editorials, 
web pages, e-mail etc. People largely access information from these online sources rather than being limited to 
archaic paper sources like books, magazines, newspapers etc. But the main problem is that this enormous 
information lacks organized nature which makes it difficult to manage. Document classification is recognized as 
one of the key techniques used for organizing such kind of digital data. Document classification is an example 
of Machine Learning (ML) in the form of Natural Language Processing (NLP). By classifying text, we are 
aiming to assign one or more classes or categories to a document, making it easier to manage and sort. This is 
especially useful for publishers, news sites, blogs or anyone who deals with a lot of content. Here, we propose a 
document classification system that can classify documents into their meaningful classes in which documents 
are very likely to have similar subjects. The proposed system extracts data by pre-processing and extracts super
topics and subtopics with the help oftf-idfand Pachinko Allocation Model (PAM) scheme. Then, the Naive 
Bayes Classifier is applied to classify, whole documents into documents with similar subjects.