Modeling "Newsworthiness" for Lead-Generation Across Corpora

04/19/2021

∙

by   Alexander Spangher, et al.

∙

5

∙

share

Journalists obtain "leads", or story ideas, by reading large corpora of government records: court cases, proposed bills, etc. However, only a small percentage of such records are interesting documents. We propose a model of "newsworthiness" aimed at surfacing interesting documents. We train models on automatically labeled corpora – published newspaper articles – to predict whether each article was a front-page article (i.e., newsworthy) or not (i.e., less newsworthy). We transfer these models to unlabeled corpora – court cases, bills, city-council meeting minutes – to rank documents in these corpora on "newsworthiness". A fine-tuned RoBERTa model achieves .93 AUC performance on heldout labeled documents, and .88 AUC on expert-validated unlabeled corpora. We provide interpretation and visualization for our models.