Editorial Algorithms: Optimizing Recency, Relevance and Diversity for Automated News Curation

With a large number of stories emerging from the newsrooms, media websites need to curate interesting news for their readers. Although traditionally news was curated solely by human editors, increasing news volume has led media outlets to adopt editorial algorithms. However, such algorithms are often proprietary, and smaller outlets do not have the resources to build them from scratch. In this paper, we present a novel framework ‘Samar’ to automatically curate news by optimizing recency, relevance and diversity of the selected stories. Evaluations over two real-world news datasets show that Samar outperforms several state-of-the-art baselines in matching the news curation performed by human editors. ACM Reference Format: Abhijnan Chakraborty, Mohammad Luqman, Sidhartha Satapathy, andNiloy Ganguly. 2018. Editorial Algorithms: Optimizing Recency, Relevance and Diversity for Automated News Curation. InWWW ’18 Companion: The 2018 Web Conference Companion, April 23–27, 2018, Lyon, France.ACM, New York, NY, USA, 2 pages. https://doi.org/10.1145/3184558.3186937