NTB Byline: an automatic article generator enabling journalists to generate hundreds or even thousands of automated articles from a single set of data and a push of a button!
A mockup of the prototype from the project report.
Olivia Louise Glittenberg from the NTB-team pitching their prototype at FutureWeek22. Video: Oliver Cameron.
"Imagine you’re a journalist working at NTB, having to write hundreds of almost identical articles every time new data is published. Then new data is published every week or even every day, and so you have to write a hundred more. The same data, the same words. Slightly different numbers and regions. During the pandemic, statistics about the number of covid-19 cases were written and published every day. But NTB had help from an automated text generator - a robot journalist."
The prototype and concept Byline has been designed and developed by the students Even Berntsen, Olivia Louise Glittenberg, Trine Mjaatvedt, Henrik Samset, Birgitte Strand and Kamilla Wigestrand as a part of MIX250, the final course of Media- and Interaction design at the University of Bergen. The team collaborated with NTB, Norway’s leading provider of text, images, video and graphics to the Norwegian media.
The challenge
The challenge the team was presented with was to develop a tool that could generate hundreds of articles based on a single set of data and a push of a button. These articles would solve their customers' need for personalized content, and the tool would be based on AI, machine learning, language processing, and automatization. The goal is that Byline will create value for NTB as it would drastically improve efficiency in-house, making journalists able to generate articles at a rate never done before.
Byline for NTB
NTB Byline is an automatic article generator for journalists at NTB. Byline elevates the basic tool that was used to generate covid-19 articles, enabling journalists at NTB to generate hundreds or even thousands of automated articles from just one data source. It allows journalists to choose datasets, edit the automatically generated articles and produce hundreds of articles that are ready for publishing within a few minutes. This tool streamlines journalistic work and helps journalists save time on articles with large amounts of data. Byline is a tool for all journalists regardless of their technical competence, and the prototype is therefore made as self-explanatory and easy to use as possible.
Byline was also the winners of this years MVP Award 2022 (Minimal viable product), which was judged by a jury consisting of representatives of the five Norwegian companies collaborating with this years students.
This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.
Strictly Necessary Cookies
Strictly Necessary Cookie should be enabled at all times so that we can save your preferences for cookie settings.
If you disable this cookie, we will not be able to save your preferences. This means that every time you visit this website you will need to enable or disable cookies again.