PUBLICATIONS
Mandeep Singh, Prof.(Dr) S.R. Dhore, Pawan Kumar, Sachin Choudhary, International Journal of Innovations and Advancement in Computer Science(IJIACS), ISSN 2347 - 8616, Volume 7, Issue 4, April 2018
We present NewsMaster, an approach to collect, cluster and categorize and select news articles from Internet. Due to the perception of cheap publishing, organizations have been producing enormous amount of content online since the hidden cost of maintenance and usability has always been neglected. This presents the opportunity for automatically maintaining crisp and usable content, especially in news articles. In this paper, we use machine learning algorithm to extract features from different classes of content and cluster them under an umbrella topic. For each cluster, we then go on to predict popularity of documents using additional features based on the content only. We conduct our experiments on different news corpuses. Our study also serves to remove information redundancy in multiple articles.