NEWSD: A Realtime News Classification Engine for Web Streaming Data

摘要

News Explorer for Web Streaming Data (NEWSD) is a GUI based text mining tool developed for the classification of streaming web data. It provides a platform to perform text mining on news updates extracted from various selected online newspapers. Initially, the text based news data is fetched from social networking pages of the selected newspapers. The real time data gathering is immediately followed by the preprocessing, feature extraction and classification. Classifiers namely NaiveBayes and J48 are employed to categorize the news updates according to their nature and semantics. The tool will lead towards a more aware society by constantly providing the relevant updates about the events.