Tag Archives: machine learning

Here are some great examples of how to use AI and satellite imagery in journalism

Leave a reply
False colour image of the Paraná River near its mouth at the Rio de La Plata, Argentina
False colour image of the Paraná River near its mouth at the Rio de La Plata, Argentina. Image: Copernicus Sentinel data [2022] processed by Sentinel Hub.

In a guest post for OJB, first published on ML Satellites, MA Data Journalism student Federico Acosta Rainis explains what can be learned from some examples of the format.

Satellite imagery is increasingly a key asset for journalists. Looking from above often allows us to put a story into context, take a more interesting perspective or show what some power prefers to keep hidden.

But with hundreds of satellites taking thousands of images of the Earth every day, it is difficult to separate the wheat from the chaff. How can we find relevant stories in this ocean of data?

Continue reading →

If we are using AI in journalism we need better guidelines on reporting uncertainty

3 Replies

Chart: women speak 27% of the time in Game of Thrones

The BBC’s chart mentions a margin of error

There’s a story out this week on the BBC website about dialogue and gender in Game of Thrones. It uses data generated by artificial intelligence (AI) — specifically, machine learning —  and it’s a good example of some of the challenges that journalists are increasingly going to face as they come to deal with more and more algorithmically-generated data.

Information and decisions generated by AI are qualitatively different from the sort of data you might find in an official report, but journalists may fall back on treating data as inherently factual.

Here, then, are some of the ways the article dealt with that — and what else we can do as journalists to adapt.

Margins of error: journalism doesn’t like vagueness

The story draws on data from an external organisation, Ceretai, which “uses machine learning to analyse diversity in popular culture.” The organisation claims to have created an algorithm which “has learned to identify the difference between male and female voices in video and provides the speaking time lengths in seconds and percentages per gender.”

Crucially, the piece notes that:

“Like most automatic systems, it doesn’t make the right decision every time. The accuracy of this algorithm is about 85%, so figures could be slightly higher or lower than reported.”

And this is the first problem. Continue reading →

GEN Summit: AI’s breakthrough year in publishing

3 Replies

This week’s GEN Summit marked a breakthrough moment for artificial intelligence (AI) in the media industry. The topic dominated the agenda of the first two days of the conference, from Facebook’s Antoine Bordes opening keynote to voice AI, bots, monetisation and verification – and it dominated my timeline too.

At times it felt like being at a conference in the 1980s discussing how ‘computers’ could be used in the newsroom, or listening to people talking about the use of mobile phones for journalism in the noughties — in other words, it feels very much like early days. But important days nonetheless.

Ludovic Blecher‘s slide on the AI-related projects that received Google Digital News Initiative funding illustrated the problem best, with proposals counted in categories as specific as ‘personalisation’ and as vague as ‘hyperlocal’.

Digging deeper, then, here are some of the most concrete points I took away from Lisbon — and what journalists and publishers can take from those.

Continue reading →

What changed in 2017 — and what we can expect in 2018 (maybe)

5 Replies

Because he sends me an email every December, Nic Newmanhas a tag all of his own on this blog. So as this year’s email lands in my inbox here’s my annual reply around what I’ve noticed in the last 12 months — along with some inevitably doomed predictions of what might happen in the next year…

Surprising in 2017: horizontal storytelling and Facebook disappointments

The rapid spread of horizontal storytelling (‘tap to advance’) struck me particularly this year. 2017 saw it become the default for new launches, from Facebook’s new ‘Messenger Day‘ feature and Medium’s Series, to Instagram‘s Carousel feature and WhatsApp‘s Status feature, while the BBC news app’s videos of the day feature used the same approach too. Continue reading →

Data journalism’s AI opportunity: the 3 different types of machine learning & how they have already been used

8 Replies

I understand that you want me to explain how Ava works (from Ex Machina)

This week I’m rounding off the first semester of classes on the new MA in Data Journalism with a session on artificial intelligence (AI) and machine learning. Machine learning is a subset of AI — and an area which holds enormous potential for journalism, both as a tool and as a subject for journalistic scrutiny.

So I thought I would share part of the class here, showing some examples of how the 3 types of machine learning — supervised, unsupervised, and reinforcement — have already been used for journalistic purposes, and using those to explain what those are along the way. Continue reading →

The machine that learns how to stop whistleblowers

1 Reply

INSIDER THREAT John connects via VPN Administrator performs ssh (root) to a file share - finance department John executes remote desktop to a system (administrator) - PCI zone John elevates his privileges root copies the document to another file share - Corporate zone root accesses a sensitive document from the file share root uses a set of Twitter handles to chop and copy the data outside the enterprise USER ACTIVITY

An example of whistleblower behaviour taken from Harry McLaren’s slides

Workplace surveillance is nothing new, but this slide from Harry McLaren’s talk on Machine Learning for Threat Detection illustrates particularly well the challenges facing journalists wishing to protect whistleblowers.

McLaren is talking about malicious threats, and the way that machine learning can be used to identify suspicious patterns of behaviour. But the example given above is equally useful in illustrating the way that similar behaviour might be used to identify an employee intending to whistleblow on illegal, unethical or dangerous behaviour by his or her organisation. Continue reading →