World News Media Network (WNMN) has announced last Thursday the winners of its Big Data and AI in Media awards during the BIGGIE Awards Ceremony in New York. At Twipe, we believe in the importance of data-driven publishing, so it’s a good time to look at some of the most innovative uses of data in media.
Robot journalism, The Washington Post
Heliograf is The Washington Post’s AI powered bot, in use since 2016. First, editors create templates for stories, with key phrases that account for a variety of potential outcomes, then they hook Heliograf up to a structured data source, for example election results. Next Heliograf identifies the relevant data, matches it with the corresponding phrases in the template, and publishes across different platforms. The system can also alert reporters of any anomalies in the data, such as wider election margins than expected, so that they can investigate.
This bot frees up journalists to work on more interesting and complex stories, while also allowing for hyperlocal news coverage, such as local high school sports.
Heliograf is creating a new model for hyperlocal coverage. In the past, it would not have been possible for The Post to staff more than a handful of the most significant games each week. Now, we’ll be able to cover any game that we have data for, giving the teams and fans near-instant coverage to read and share.
Jeremy Gilbert, The Washington Post’s director of strategic initiatives
In its first year, Heliograf published 850 articles and generated more than 500,000 clicks.
Daily deep insights in the newsroom, Twipe
Supported by Google DNI, EngageReaders provides the newsroom and product managers daily insights on content and composition of their digital editions. Through predictive modelling, EngageReaders identifies Overperforming and Underperforming articles and highlights Hidden Gems. EngageReaders emerged as the result of a collaborative research initiative in 2015 between Twipe, KU Leuven, imec, and Mediahuis.
The judges said about EngageReaders:
That is a creative approach using modern market research methods to baseline engagement. In this sense the work is about recommendations. Excellent work!
AI to generate revenue and boost engagement, Ringier AG
Ringier AG was recognised for its innovative use of advanced artificial intelligence to both generate revenue and boost user engagement. In order to obtain an in-depth understanding of customers’ interests and needs, a central data and technology platform was created. It contains both content profiling and interest profiling, allowing for supercharged personalization to increase engagement and revenue.
Through this platform, content recommendation links on articles have been fully automated, with a 32% higher Content Click-Rate than manually chosen recommendations from the editorial team. Furthermore, content recommendation that has been personalized using individual interest profiles has generated a 46% higher Content Click-Rate.
What differentiates this platform from other products is the large-scale, coordinated use of AI, including Natural Language Processing, Sentiment Analysis, and Taxonomy Classification.
This article was written by Mary-Katharine Phillips, Media Innovation Analyst at Twipe from 2017 – 2021.