In information systems, tags are keywords or terms, which represent a piece of information. They provide to define an item and help it to be found again through searching or browsing. Tags have gained popularity due to the growth of social sharing, social bookmarking, organization network and social network websites. In addition, tags are also used to express prominent events and noticeable topics in the news. In this thesis, we propose a tag-based statistical learning approach to predict the shareability of news in an organization network. We represented features with tags by using different methods and adopted several classifiers to predict the shareability of news. We model this problem with a binary classification problem, where shareable news are considered as the positive and non-shareable news are considered as the negative class. The experimental results indicate that there is no general best classifier for the study of shareability prediction for organization related news but depending on the dataset and represented features we can adopt an optimal classifier.