How publishers are experimenting with more homepage personalization sections

At the end of March, The Washington Post added an individually personalized “For You” section on the homepage to subscribers and registered users, after seeing success with the “For You” tab in its app. The news publisher also plans to roll out a new personalization feature next month aimed at retaining subscribers. While Coleen O’Lear — who was promoted to become the new head of curation and platforms in January — declined to share further details about the upcoming feature, she said it will “make it a lot easier to track what you’ve already read on our website and our apps.”

“Someone who’s coming [to the site] frequently, wants to know whether that story that they read before has been updated, or whether they should read something new. We’re really trying to help people start that journey as well,” she said.

The New York Times created a new “experiments and personalization” team earlier this month to experiment with personalizing the homepage on the Times’ website and app to get subscribers to read more stories. The team is working with editorial desks and product teams to test targeting readers based on their location or reading history, and is doing “active tests” in a module called “In Case You Missed It” — “to showcase some of the breadth of work that we have, as well as amplify some of the strongest pieces,” said Derrick Ho, deputy editor for personalization, who is leading the experiments and personalization team.

The Washington Post’s ‘For You‘

The Washington Post’s “For You” section combines a reader’s selections made while onboarding (when a subscriber or registered user signs up, they can select their topic preferences), reading history and data on stories’ performance on different platforms (O’Lear declined to share more details about the last signal). The more a reader engages with the “For You” section, “the stronger it gets,” O’Lear said. The algorithm can provide better suggestions tailored to what a person chooses to read.

“Relevance is a really important aspect of building a stronger reader experience,” O’Lear said. “What’s most critical is that we serve the right thing at the right time. That’s really about balancing impactful curation with smart personalization.”

‘ICYMI‘

An algorithm powers the “In Case You Missed It” module on the homepage below the Opinion section on The New York Times’ homepage, but editors select the pool of stories to show up in that section. If an article was read in the past 30 days, it will not be shown to a reader again in this section.

The Times has also tested geo-targeted content packages for segments of readers, such as giving visitors from California an extended package during Gov. Gavin Newsom’s recall election last year. The team has also considered providing local content recommendations, such as showing emergency location information during California wildfires for those who live in the state, said The Times’ associate managing editor Karron Skog.

Much of that is still on the horizon. “We’re still very much in the phase where we are trying to build the tools, and refine the tools. We are researching and doing a lot of user research,” Ho said.

Why news publishers are prioritizing personalization

While executives and editors at both The Times and The Post insisted most of their homepages will rely on manual curation to package the biggest stories of the day, sections and modules with personalized content can help take the pressure off editors and surface relevant content, which those teams believe can lead to better reader engagement, conversion and retention.

The Times, for example, publishes about 200 URLs per day. “No reader can get through 200 pieces a day. We are trying to use some of this work to really put the right things in front of the right readers at the right times,” Skog said.

As the Times’ subscriber base has grown to 8 million digital subscribers, leaders there want to scale a good homepage experience. “And this is one way that we can do it,” Ho said. “We want that experience to be far superior than what they can get from one of our articles that’s found in the wild.”

Personalization gives the Post an opportunity to convert readers to subscribers, as well as provides “good retention value for subscribers,” especially for those who come to the site frequently, O’Lear said. “It’s really important for them to see something new when they come.”

That’s also a priority at The Times. As stories move on and off the homepage, it’s easy for a reader to miss a big story, Skog said. An algorithm can help differentiate between subscribers who are visiting the site once a week or 10 times a day. The new team at the Times is working “to really make sure that readers see the things that we think are important on any given day, no matter when they visit us,” Skog said. “For me, that’s something that we wished we could do for a really long time.” Skog did not say how the team was identifying these readers.

There are two ways personalization can benefit both a publisher and a reader: it helps publishers compete with the algorithms of tech and social media platforms like Amazon and Twitter, and it can surface different content based on what the reader has (or hasn’t) already seen on a publisher’s website, leading to a better user experience, said Adam Singolda, CEO of content recommendation platform Taboola.

In January, Taboola announced a new product called “Homepage for You,” which adds a layer of A.I. to a publisher’s website to surface relevant and personalized content to match readers’ interests, which Taboola says can result in increased readership and engagement. It’s being used by publishers like McClatchy and The Independent. In a beta test, publishers saw a 30%-50% increase in CTR for homepage sections personalized by Taboola, according to the company.

“Most of the platforms people are consuming media on are already completely personalized, like Twitter and Facebook,” said Jeff Kupietzky, CEO at multichannel monetization and engagement platform Jeeng (formerly known as PowerInbox), which helps publishers gather reading history data on its site visitors to then be able to match content recommendations with a specific person’s interests. The algorithms that power the content people see on their timelines and newsfeeds are what they have come to expect, Kupietzky argued.

“There is likely a reader for every story we publish, and we’re just trying to find those readers,” Skog said.