Nick Evershed, a 2016 Walkley Innovation Grant winner, explains why he’s trying to automate news reporting.
These days, reporters have less time than ever. And, despite having less time, journalists often have to write formulaic stories. Such as covering the weather — how hot is it? Is it a new record? Or recurring stories like politician’s expenses and political donations. Who spent the most? Who are the top five? Were donations more or less than last year?
These types of stories also require some mathematical analysis, which can tie up other resources in the newsroom. Journalists would prefer to be spending time on deeper, more meaningful investigations. Like why is the climate is changing, and how does it affect people? Or, for a current example, which politicians are abusing the expenses system?
This is an issue.
Here’s an idea – when the labour new unemployment figures come out from the ABS, what if you had a program that could automatically get the data, compare it with historical data, and then give you three or four pars on what’s changed and how? This would free up the newsroom to do more on the story, like putting the figures in context with global conditions and government policy, or putting a human face on the figures.
My plan is to build a system that can automate the analysis, writing, and production of graphics for these formulaic stories. Data in, news story out. Because one thing that these recurring stories have in common is that they involve data.
This isn’t an original idea, and there are companies that are already doing it. But these are either proprietary commercial services, or built for specific types of data. Two of the more prominent companies in this area are Narrative Science and Automated Insights. An excellent specific example in journalism is the LA Times’ Quakebot.
If the news media want to control how technology like this is used and how it affects their industry, it’s far better to construct an open-source system that can be used by any media organisation.
Myself and my colleagues initially prototyped a version of this called Time Serious at the Walkley Editors Lab hackathon in 2016. Now, I’m taking the idea forward with under the name Reportermate (you know, like report automate, reporter mate, etc.). You can check out the very rudimentary website here.
In the next few months I’ll be conducting research on breaking down data-centric news stories into modular templates, prototyping an application, and looking around for interested developers who might be keen to contribute to the project. If this sounds like you, then please get in touch: firstname.lastname@example.org.