Welcome to the latest Newsroom Initiative newsletter.

Newsrooms all over the world are experimenting with AI, and one in New Zealand has already published thousands of stories built using generative-AI run across stock exchange announcements, a relatively safe sandpit to experiment in as you will see.

Oddly, there’s another New Zealand story this week, a follow up to a damaging editing scandal at the public broadcaster Radio New Zealand, which I suspect offers salutary lessons for anyone leading a news organisation or running a newsroom. Check your procedures.

Business news site runs generative AI across thousands of stock filings

Stock exchange announcements have long been ripe for what we used to call computer-assisted journalism and what we can now process through generative AI. They’re clearly formatted and relatively easily parsed. They also matter.

Several decades ago Reuters trialed an automated extraction of journalistic value from stock exchange filings and, of course, it has come a long way since then.

A small-but-innovative New Zealand business news site, BusinessDesk, has led the way in the contemporary use of generative AI in that country, and, sensibly, it has focused initially on historic and current announcements to the stock exchange.

By running nearly 3,000 announcements through generative AI, the site has created a historic database that underpins the value of stock data and news its readers rely on to trade. It also cuts to 30 seconds from half an hour the time it takes to create an article based on a statement.

I suspect it is only the start, but it seems to me a sensible place to start: Stock exchange filings have a consistent format with little room for error, the corpus can be tested in chunks to confirm accuracy, it can be dreary for humans (though stories are often hidden in them).

I talked to Matt Martel, the publisher and general manager of BusinessDesk, about his decision to launch this experiment in Artificial Intelligence, which rapidly became a publishable product. BusinessDesk was acquired two years ago by INMA member NZME. 

This interview has been edited for clarity and brevity.

INMA: How are you collecting and extracting the value from this and converting it into publishable stories?

Matt Martel: We launched NZX [New Zealand Stock Exchange] data on the Web site two years ago, and we’ve stored every announcement on a server since then. In December, we wrote code that allowed us to push anything we wanted to ChatGPT and for it to return as a JSON format that we could automatically ingest into our CMS.

There were 2,700 announcements sitting in our database on day one, and we went through and summarised those as news stories. So that was 2,700 articles in an hour. We weren’t happy with some of the results so we tweaked the prompt and did it again. We then attach each article to our stock market graphs and show which announcements have moved the market.

INMA: Presumably because you’re putting specific content into ChatGPT, the risk of hallucination is much less and so you can rely on it being accurate?

Matt Martel: That’s right, to an extent. If we send an announcement that’s missing a full stop at the end, it will send something back that fills in the rest of that sentence with hallucinations … . It’s still trying to hallucinate and build things in if we don’t have a full stop at the end of the last paragraph.

When we start asking it to do things such as write an article as a business reporter, or to put it into Guardian style, or to do things which are more than summarise the article, then it starts to just do too much. All we wanted it to do was a very basic job to summarise this announcement as a news article. And it does a really nice job of that.

INMA: What has this saved you in terms of editorial resources?

Matt Martel: At this stage, this is just for the NZX data so our journalists don’t need to be involved in editing and moderating the content that comes back. But we absolutely keep an eye on it. We read everything but after publication. We were running the system on our test servers and tweaking it for months before launch, so we were pretty confident about it. We are asking it to take a single piece of content from an NZX announcement and then create a news article. AI is really good at that.

But we’ve had to learn how to work ChatGPT and now Bard. This has our data editor, Andy Fyers, learning how to create the correct prompts for the articles. The next stage is to get ChatGPT to start writing headlines for us, which will be live shortly.

INMA: And you’ve associated those historic items with movement in the stock that you can now associate with the charts on each stock, right?

Matt Martel: We’re hoping to show which announcements have moved the market, and our goal is to also append our own stories to the charts. One day we want to be big enough to show that our journalism also moves markets.

INMA: What other uses are you imagining?

Matt Martel: Where it will be interesting is for fact-checking, where we can say this fact looks like it’s not correct because it differs from what we’ve previously published. That also then allows us to create category pages or topic pages so any proper noun can then become a topic page, which will help with search discovery.

INMA: I see you label whatever you have used Artificial Intelligence to create.

Matt Martel: We’re very clear when we have used AI and it’s almost as simple as that. We need to declare whatever we do.

INMA: Matt, I think you have a clear idea why you need to leap on AI train now?

Matt Martel: We’ve seen this from the demise of newspapers and the rise of the Internet. It’s going to happen anyway. So you’re probably going to be involved. I’d rather be at the forefront of it and understand it than in three or four years realise that our competitors have done the same thing or someone new has come along and destroyed our business model.

Radio New Zealand to merge digital and news teams after editing scandal

Radio New Zealand says it accepts and will implement in full a set of recommendations on its newsroom methods after a scandal over edits to Reuters and other international agency stories that shifted context and added background — in some cases in line with Kremlin talking points.

In an earlier post I wrote about the case for the INMA Newsroom Initiative believing it has lessons for all newsrooms.

Perhaps most surprising is that RNZ says it will now combine its radio news operation with its digital newsroom, having kept them separate for years after most news organisations realised digital was a crucial part of the newsroom and not an add-on with different standards.

RNZ has launched changes in the wake of a report from independent advisers called in to investigate how and why dozens of online news stories were found to have edits that added context that was out of line with what had been in the original from Reuters or other services.

The public broadcaster, which just received a 60% increase (NZ$26 million US$16 million) in its budget from the government to expand online services just as the scandal broke, has audited the work of the single editor involved in the case who has since resigned. It also has reposted dozens of stories with the edits removed and explained.

Comments from the investigators within 22 recommendations included uniting the radio and digital news operations address, the motives of the editor involved, and public remarks by the RNZ Chief Executive Paul Thompson, who described some of the problematic content as “pro-Kremlin garbage.” The investigators said that “contributed to public alarm and reputational damage.”

In my view, having read many of the stories, he was and remains on the mark and tried to get ahead of what was an inevitable pile-on by rival media.

The investigatory panel also said it “accepts that the person responsible for the inappropriate editing genuinely believed he was acting appropriately to provide balance and accuracy, and was not motivated by any desire to introduce misinformation, disinformation or propaganda.”

That may surprise those who read some of the edits and called out the shift in tone.

RNZ said has said it will appoint a senior leader to oversee editorial standards.

Here are a couple of extracts from the investigation that may be relevant:

• “While the inappropriate actions were those of an individual journalist, the wider structure, culture, systems, and processes that facilitated what occurred and responded to it are the responsibility of RNZ’s leadership.”

• It found a “busy, poorly resourced digital news team” and a lack of “consistency and effectiveness” in editorial training in an unsatisfactory editorial structure.

• “Outdated technology, organisational silos and a lack of trust between the digital news team and the traditional newsroom are all cited by staff as issues of concern and the panel agrees. These factors all potentially create information and/or trust gaps and reduce effective communication and oversight of editorial standards.”

The full report is here, and I suspect many organisations would recognise themselves in parts of it or be grateful that they have taken action to avoid similar pitfalls.

About this newsletter

Today’s newsletter is written by Peter Bale, based in New Zealand and the U.K. and lead for the INMA Newsletter Initiative. Peter will share research, case studies, and thought leadership on the topic of global newsrooms.

This newsletter is a public face of the Newsroom Initiative by INMA, outlined here. E-mail Peter at peter.bale@inma.org or newsroom@inma.org with thoughts, suggestions, and questions.

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .