Dynamic News Classification Using Machine Learning

2198 Words Oct 13th, 2016 9 Pages
Dynamic News Classification using Machine Learning

Introduction
Why this classification is needed ? (Ashutosh)
The exponential growth of the data may lead us to a time in future where huge amount of data would not be able to be managed easily. Text Classification is done through Text Mining study which would help sorting the important texts from the content or a document to manage the data or information easily.
//Give a scenario, where classification would be mandatory.

Advantages of classification of news articles (Ayush)
Data classification is all about tagging the data so that it can be found quickly and efficiently.The amount of disorder data is increasing at an exponential rate, so if we can build a machine model which can automatically classify data then we can save time and huge amount of human resources.

What you have done in this paper (all)

Related work

In this paper [1] , the author has classified online news article using Term Frequency–Inverse Document Frequency (TF-IDF) algorithm.12,000 articles were gathered & 53 persons were to manually group the articles on its topics. Computer took 151 hours to implement the whole procedure completely and it was done using Java Programming Language.The accuracy of this classifier was 98.3 % .
The disadvantages of using this classifier was it took a lot of time due to large number of words in the dictionary. Sometimes the text contained a lot of words that described another category since the…
Open Document