Category: Uncategorized

The Schibsted newspaper Bergens Tidende is an insight-driven news organization. Their audience engagement team is using computer vision to give female readers more relevant content. From their experience, pairing high- and low-tech solutions is key to success.

The small and agile audience engagement team based on Norway’s southwestern coast delivers quantitative insights, data analysis and other solutions enabling editors to showcase journalism in new ways and helping journalists make smart choices in their work. To better serve their broad group of readers with relevant and engaging content, Bergens Tidende (BT) strives for more diversity in their news coverage. A key aspect of this effort is to make BT more relevant to women across various ages.

Insights from computer vision

In an effort to get more female readers and subscribers, BT is using computer vision to better understand who they are telling stories about, and specifically, what people the imagery on their website depict. By estimating the age and gender of faces used in an article’s imagery, BT’s application of computer vision enables insights into how their news coverage relates to the demographics of their audience. Adrian Oesch, data scientist in the audience engagement team, has been leading the work.

“In general, I think it’s super interesting to explore how technology can help improve our understanding of newsroom processes. In this particular case, we saw computer vision as a valuable method because it’s essentially automating a repetitive task we could have spent manual – human – resources on,” says Adrian Oesch.

And numbers show that the share of female readers increases as the share of images with females does. Coincidence? We think not.

Image recognition is not the only tool employed in order to shift towards more representative news coverage. BT has, for example, studied what topics/themes are most read by men or women, elderly versus younger, and locally versus nationally. These are just a few of the efforts made to diversify the content produced.

Young women give their input

Hanne Louise Åkernes, deputy news lead in BT, is running an effort called Project Silje together with political commentator Gerd Tjeldflåt. Project Silje could be seen as a more low-tech equivalent to the image recognition solution. Through creating a physical and digital arena for young women to meet and discuss news topics relevant to them, Åkernes and colleagues are extracting learnings about how to create editorial content that makes young women connect more with what is written in BT.

“At times I worry that media organisations forget to listen to what readers really care about. In order to attract a new generation of news readers, we need to open up for readers to tell us what kind of content they want to consume!” says Hanne Louise Åkernes.

Through an online survey, a Facebook-group and physical discussion events, Åkernes and her BT colleagues have so far given about 5,500 women aged 25-40 the opportunity to tell them what they are interested in learning about through the news.

“This new way of interacting with our readers gives us an opportunity to dig into topics that really matter to our target audiences. So far the content produced through this process has performed very well in terms of clicks and conversions,” Åkernes explains.

A hotbed for new solutions

The combination of quantitative and qualitative user insights, paired with an organization that loves testing new solutions make BT a hotbed for new journalistic solutions. To be able to work for more diverse representation in the media, BT is now exploring what other tools might provide journalists and editors with the opportunity to make more informed choices.

Distribution Innovation wants to use new technologies in ways that make sense for both people and the planet. With the help of AI they are working to minimize their environmental emissions, but they are convinced that humans still make the best detectives.

Distribution Innovation (DI) is part of the Schibsted family* and is the leading Nordic logistics and subscription technology service provider. With more than 2.2 million products going through its system every day, DI is working with billion-dollar companies and local publishers alike. Simply put, DI manages the entire value chain from order to delivery into the hands of the consumer. While the company is still unknown to many, DI serves 2.5 million households in Norway, 3.8m in Sweden and 1.2m in Finland.

ML Optimizes newspaper delivery

As millions of packages and papers are to be distributed through the systems on a routine basis, planning, prediction and optimization are all vital. Solving such tasks are often described as the perfect job for AI, and the successful implementation of AI across the DI value chain indicates a belief in that very idea. So what’s the key to DI’s work with AI?

“If you ask me, we have been very good at applying these new technologies in ways that make sense for both people and the planet”, says Frode Finnes Larsen, CTO at DI.

So what makes sense for the planet? One idea could be to not waste our world’s resources on newspapers that won’t be read. To explain how DI works to do this, let’s look at an example where AI, or in this specific case, Machine Learning (ML) is used to optimize newspaper deliver.

Every day newspapers are sent from DI’s distribution centres to various retailers such as Seveneleven or Narvesen. If there are unsold papers at the end of the day, they are sent back to the central and the retailers get a refund for the returned copies. A key challenge for DI here is to make sure that the right amount of papers go to each store every day. Enter stage, ML!

Through an ML solution that predicts how many papers a specific store will sell during a given day, the DI system informs not only the distribution (i.e. how many papers are sent to each store) but also the printing of newspapers.

Identifing the most efficient route

Another example of AI put to use for environmental good is that of DI’s route optimization tool. Last mile delivery, or put differently, being able to deliver papers and packages to people’s doorstep is another key aspect of the DI service. Every day, delivery employees are assigned to various routes with delivery points along the road. Regardless of whether the delivery employee is driving a truck, riding a bike or walking, the DI system uses an AI system trained on geographical- and address data in order to optimize the route and ensure that the most efficient path is taken. This AI-powered planning tool is particularly important for the delivery routes of cars and trucks, as the optimal route will minimize fuel use and reduce co2 emissions.

“The beauty of our model is that it focuses only on the delivery point. It does not care about the name on the door,” says Frode Finnes Larsen, highlighting the fact that the AI solution does not discriminate by for example prioritizing clients or neighborhoods, but seeks to generate the optimal route in order to save resources.

Using digital tools across delivery systems may seem like a given today, but the fact is that many otherwise highly digitalized markets still use analogue solutions like paper slips and log books for deliveries. DI has been employing digital solutions since its start back in 2001 and has no plans on stopping.

“Employing digital technologies is embedded in our DNA,” says CTO Frode Finnes Larsen.

Innovation is core business at DI. As history has shown, the distribution company is keen to employ new technologies and tools across the business to make life easier for customers and employees alike. As noted by Muhammed Sadjit, who has been working at the distribution centre in Nydalen, new technologies continuously help employees do their jobs better and faster.

“That makes me happy,” says Muhammed.

While DI has an ambition to further explore AI and its potential, many tasks along the value chain still require the very unique skill set of human beings. One such task is found in what is internally known as “the brainy station” at the distribution terminal in Oslo’s Nydalen. At the brainy station, Employees manually investigate faulty packages or parcels that have not been able to get delivered.

Here, data and insight tools are used as support for a task requiring human expertise. According to Jovana Vrcelj, a distribution employee at the Nydalen terminal, the work done at the brainy station is based on the skill of understanding irregular mistakes. By reflecting on human made errors like for example misspelled addresses or poor handwriting, Jovana and her colleagues step in to make sure that every parcel finds its rightful destination. She describes the work as similar to that of a detective sorting through clues.

“Humans make the best detectives,” says Jovana and digs into another mystery.

* Schibsted owns Distribution Innovation together with Amedia

Read more about DI in Schibsted Future Report 2020

At Schibsted we use AI to build the best possible digital products and services for our users, and to ease the work of our employees. We believe that transparency is key as we work with AI and that is why we want to share some examples of how we are working with these new technologies.

Our company is based on a long tradition of independent news, information and transparent marketplaces. Trustworthiness and quality are core to what we do, and when using new tools such as artificial intelligence (AI) Schibsted is dedicated to ensuring that our implementation and experimentation represent these ideals.

From theory to practice

In 2019 the EU presented a set of guidelines on trustworthy AI (read more about them here). These guidelines offer great basis for theoretical discussion, but we need to make sure that we collectively – as nations, industries, companies – are able to bring them to practice. We believe organizations such as ours have a responsibility to show how trustworthy AI might look in practice.

With some case studies we want to provide concrete examples of how we are using AI as a tool to empower consumers, citizens and employees in their everyday lives. We want to be transparent and give readers insight into how various aspects of AI are improving our product and service offerings.

The potential benefits of using AI across the Schibsted portfolio are countless. We start by sharing the stories about how Distribution Innovations works with AI to minimize their environmental footprint, how Bergens Tidende uses computer vision to identify gender biases in news reporting and how the Prisjakt price index staff is empowered through machine learning.

 

Read more on how we work with AI

 

Prisjakt helps consumers across seven countries to make more informed purchasing decisions. The team behind Prisjakt is dedicated to transparency, and now machine learning is helping them scale it.

Prisjakt is a price- and product comparison site with the goal to guide consumers into making smarter purchasing decisions. The company started as a hobby effort in the southern Swedish town of Ängelholm back 2002. Today Prisjakt has grown into a 230-people strong company dedicated to provide consumers with as good pre-purchase information as possible.

The user experience on Prisjakt is built around the idea of having all relevant information in one place. This means that if a consumer is looking to buy the latest iPhone, all the retailers selling that iPhone should be displayed in the same interface, “the product page”.

Creating relevant product pages requires intense indexing work where identical products from all reachable e-commerce sites have to be connected. Usually, this connection is done through industry product codes such as European article number (EAN). If a product lacked this type of code the Prisjakt team would previously sort them manually.

This is where Machine Learning (ML) comes into the story.

Scaling reach through ML

Through ML, the sorting of codeless products now happens automatically. This might seem like a small task, but let’s revisit the fundamental product offering of Prisjakt. The goal of the service is to display all the prices of a given product. Can you imagine the amount of data such an endeavour in the case of an iPhone might generate? Every day? Every hour? You get the idea.

A common challenge for machine learning solutions is to ensure sufficient amounts of data for models to train on. In the case of codeless products, there is usually a lot of data to be found on popular products (such as an iPhone). For less common products, let’s say a Game of thrones collector’s item, there are not that many past examples (i.e. not a lot of data) for the model to learn from.

In order to cater to eventual shortfallings of the machine learning model, which often related to there not being enough past examples for the model to learn from, the staff of Prisjakt still “own” the indexing and could manually change any connection made by the machine, or shut the feature off altogether. Keeping humans in the loop is essential to the success of the model and an important strategic decision by the Prisjakt team – both in terms of delivering product quality and protecting the agency of employees.

Empowering the team

Grzegorz Drozdowski works in the indexing team at Prisjakt’s Krakow office. He thinks the new ML solution enables his team to spend their days working in a more efficient way:

“The best part is that we got rid of some monotonous work, which ML does. We can now focus on things like the correctness of the data we present or having all available offers under the most popular products,” says Drozdowski.

While the idea of getting rid of monotonous tasks might indicate that working at Prisjakt used to be less innovative, Drozdowski is quick to highlight that coming up with new ideas and finding new ways to provide value is part of the Prisjakt culture.

“There has always been time for being innovative in our company”, he says.

Finding new ways to add transparency to the purchasing experience is built into the DNA of Prisjakt. As noted by Grzegorz Drozdowski, the Prisjakt team is excited to explore new ways of utilizing AI technologies for providing an even better customer experience in the future.

”To inspire the kids to keep coding, is the absolute most fun thing about Kids Coding Camp”, says Johanna Nilsen one of the teachers at Kids Coding Camp.

Usually Johanna is a student at KTH, the Royal Institute of Technology, in Stockholm where she’s studying to become an engineer in media technology. When she learned about the coding camp at a fair at school she immediately knew she wanted to work with it.

”I liked the idea of the camp and also the possibility to work at Schibsted.”
Together with other university students she has worked as a coding teacher at Kids Coding Camp and has now participated in educating some 60 kids.
And she has also been having fun – during the camps they do everything from playing games to programming and solving problems.

”The engagement from both parents and kids is amazing. It is incredible to watch the kids grow, learn new stuff and being so curious to know more”, says Johanna.

Different level of knowledge

Some of the children have never been block programming before, others do it every week in school. Johanna herself knew early on that she was into technology, finding maths fun and pretty easy. She went to a technology high school in Gothenburg which gave her the chance to apply to KTH.

”I knew I wanted to study something challenging and media technology is both creative and technological. I’m studying things like machine programming, applied computer science and interaction between man and machine”, she explains.
But she has also learned a lot at Kids Coding Camp.
”Above all how you teach people who have never programmed before how to get started with a project. This, I think, will really be useful for me in my own career.”

So what is the coolest idea that has come out of the camp this far?
”There are so many! But one of the youngest girls really made an impression on me. She was into storytelling and programmed a video with characters she had drawn herself. The way she developed the story and created alternative endings was very impressive”.

Schibsted wants to give more kids the opportunity to learn the languages of tomorrow. That is why we arrange Kids Coding Camp.

It all started in June 2019 when the atmosphere in our offices in Stockholm and Oslo changed completely – kids aged 8-12 years invaded the buildings, spending a week with us to learn how to code and use coding to solve challenges. This camp was just the first step on an exciting journey, and we started out with inviting our employees’ children. In February 2020 we organized two more camps to which we invited kids with no connection to Schibsted, and this summer we are planning for two more camps with ”Schibsted children”.

”I couldn’t imagine that this was going to be such a success when we started this initiative. We are now planning our fifth and sixth coding camp that will take place in Stockholm and Oslo this summer and we believe that we can make a difference for the future”, says project lead Kamilla Abrahamsen.

She is proud to facilitate an important Schibsted’s initiative: Making sure the next generation is even more tech-savvy and able to navigate through and benefit from new technology than their parents.

Rethinking tech through the kids

In Schibsted, tech is an integrated part of all we do and technology is developing faster than anyone could have anticipated just a few years ago. If we are to take advantage of these new possibilities, we need to teach our kids to master the basics, as well as encourage them to dream big.

Through Kids Coding Camp, Schibsted wants to engage and inspire kids and youths to envision that they can affect the future and that technology can be a tool to find solutions we need when they grow older. And not least, we want to give hope and confidence, in a world with lots of challenges and where kids worry about the future. To address this we also dedicate time to discuss how innovation and tech can help out when it comes to environmental issues.

One of the great things about coding is that it gives the same opportunities to all regardless of gender, social background or other prerequisites. By arranging Kids Coding Camp, Schibsted also wants to lift the importance of equalizing differences and giving people the same opportunities to educate themselves, grow and flourish.

”The “secret code” to securing the best tech-heads for our future is to make sure kids are not held back because of circumstances beyond their control. We want to empower these kids and It’s a human right to have equal opportunities”, says Britt Nilsen, Head of Sustainability at Schibsted)?.

Listen to what the kids thought about the camp – and about girls in tech, below.