Finding and expressing news from structured data

In the age of increasing floods of information, finding the news signals from the noise has become increasingly resource and time intensive for journalists. Generally, news media companies have the important role of filtering and explaining this flood of information to the public. However, with the increase in availability of data sources, human journalists are unable to catch and report on all the news. This limitation, coupled with the need for media companies to continuously provide value to news readers, calls for automated solutions, such as automatically generating news from data. In order to support the journalists and media companies, and to provide value to audiences, this work proposes approaches for automatically finding news or newsworthy events from structured data using statistical analysis. Utilizing a real natural language news generation system as a case study, we demonstrate the feasibility and benefits of automating those processes. In particular, the paper reveals that through automation of the news generation process, including the generation of textual news articles, a large amount of news can be expressed in digestible formats to audiences, at varying local levels, and in multiple languages. In addition, automation allows the audience to tailor or personalize the news they want to read. Results of this work thus support and broaden the news offering and experiences for both media companies and the public.