Prediction & Evaluation of Online News Popularity using Machine Intelligence

News popularity is the maximum growth of attention given for particular news article. Social networking websites, news websites are used for reading different news. Online news popularity depends upon various factors such as number of shares on social media, number of comments by visitors, number of likes etc. So it is necessary to build an automated decision support system to predict the popularity of news as it will help in business intelligence too. The work presented in this research intends to find the best model to predict the popularity of online news by using machine learning methods. Initially, LDA is used to reduce the dimension. Then three different learning algorithms such as AdaBoost, LPBoost, and Random Forest are implemented in order to predict the news popularity. The performance of system is tested on the dataset which comes from UCI machine learning repository. The prediction performances of all three methodologies are studied by considering evaluation measures. Adaptive Boosting turns out to be the best model for prediction and it has achieved accuracy of 69%, F-measure of 73%.