Information prioritization plays an important role in the way we perceive and understand the world. Homepage layouts, which are daily and manually curated by expert human news editors, serve as a tangible proxy for this prioritization. In this work, we present NewsHomepages, a novel and massive dataset of over 3,000 news website homepages, including local, national, and topic-specific outlets, captured twice daily over a five-year period. We develop a scalable pairwise preference model to capture ranked preferences between news items and confirm that these preferences are stable and learnable: our models infer editorial preference with over 0.7 F1 score (based on human trials). To demonstrate the importance of these learned preferences, we (1) perform a novel analysis showing that outlets across the political spectrum share surprising preference agreements and (2) apply our models to rank-order a collection of local city council policies passed over a ten-year period in San Francisco, assessing their “newsworthiness”. Our findings lay the groundwork for leveraging implicit cues to deepen our understanding of human informational preference.

Journalists regularly make decisions on whether or not to report stories, based on “news values”. In this work, we wish to explicitly model these decisions to explore _when_ and _why_ certain stories get press attention. This is challenging because very few labelled links between source documents and news articles exist and language use between corpora is very different. We address this problem by implementing a novel _probabilistic relational modeling_ framework, which we show is a low-annotation linking methodology that outperforms other, more state-of-the-art retrieval-based baselines. Next, we define a new task: __newsworthiness prediction__, to predict if a policy item will get covered. We focus on news coverage of local public policy in the San Francisco Bay Area by the _San Francisco Chronicle_. We gather 15k policies discussed across 10 years of public policy meetings, and transcribe over 3,200 hours of public discussion. In general, we find limited impact of public discussion on newsworthiness prediction accuracy, suggesting that some of the most important stories barely get discussed in public.Finally, we show that newsworthiness predictions can be a useful assistive tool for journalists seeking to keep abreast of local government. We perform human evaluation with expert journalists and show our systems identify policies they consider newsworthy with 68% F1 and our coverage recommendations are helpful with an 84% win-rate against baseline. We release all code and data to our work here: https://github.com/alex2awesome/newsworthiness-public.