As time goes on, digitization of text has been increasing day by day and there is a need to classify them. Text classification has become very essential in this situation. Text analysis is used for information extraction, information retrieval and pattern recognition. The problem of text analysis is, it takes much amount of time to complete work as various methods and various algorithms are being used in this process. Each method being used in the classification has different accuracy rate. The idea of the project is to compare different machine learning algorithms and to find the best possible solution for the highest accuracy. To evaluate the model efficacy, News Articles dataset from kaggle has been used. Then, the input can be given as different News Articles and these News Articles are filtered into different categories according to their genre i.e., sports news, business news, health news, world news etc. The machine learning algorithms can be Naive Bayes’ classifier, Support Vector Machine and Neural Networks which are being compared to get the accurate result. The above comparison can be represented using graphs. This will help in searching the News, category wise.
Volume 11 | 07-Special Issue
Pages: 1423-1426