In current scenario, lot of online news is available for different topics on Internet from which textual data is increasing rapidly. Due to this, it becomes essential to organize them properly so that important news can be searched easily as well as to avoid data loss. One effective solution for this problem is to classify the news into different classes or to extract most important and useful information. This paper is an attempt to provide a solution for by classifying the news text into different classes. For this, two different machine leaning algorithms (Random Forest and Decision Tree) are used. Experiment is performed on an online dataset taken from Kaggle to analyze which algorithm can be used to provide better results.
Key words: News, text, machine, learning, Random Forest Decision Tree
|
