Archive for the ‘Data Science’ Category

Two weeks ago, Facebook opened up its Instant Articles platform to all publishers. And last week, Facebook announced that they will be updating their News Feed algorithm once again. The most recent change to their algorithm will look at predictions of whether a user in the Facebook mobile browser or on an Instant Article page will click into an article and actually read that article. Time spent viewing the article will continue to be a large factor in News Feed rankings.

When Facebook makes changes, the publishing industry reacts with questions and concerns (see, for example, here, here, or here). That said, each time we here at Chartbeat have looked at Facebook referrer traffic in response to one of these changes, we haven’t seen any major effect across our network.  Here’s what the median percentage of traffic from Facebook looks like across our network so far this year:


Besides the typical weekday / weekend variations, traffic from Facebook is remarkably stable. We see Facebook driving between 40-50% of traffic on mobile devices during peak weekday traffic and about 12-15% of traffic on desktop devices during peak weekday traffic (note that these numbers exclude cases in which we have no data for referrer, as is the case for dark social). Even given the two big changes that happened this month, we are actually seeing a slightly higher-than-normal amount of referral traffic! This increased traffic is on the order of 3-4% for the median (smaller if you look at the average; 1%).

It is important to note that these curves show the median proportion across our network. Individual sites respond in different ways, so you may have seen your traffic rise or fall in response to one of these changes. Sitting in the newsroom, it is hard to see the forest for the trees, so to speak — we have the power of statistics on our side. But from what we continue to see, the majority of publishers are incredibly adept at responding to Facebook’s changes and are keeping referral numbers high.

Beginning several days ago (the evening of Tuesday, 1/20, to be precise), you may have noticed a significant increase in the traffic on your site from LinkedIn: across our network, traffic from increased by over 3x. Below, we’ll detail why that change occurred, and what publishers should expect going forward.

Over the past year, publishers have become increasingly interested in traffic from LinkedIn, as the LinkedIn team has been steadily working to improve their feed experience with the launch of their new mobile app and content platforms. Nevertheless, when looking at referrer traffic in analytics tools like Chartbeat, web traffic from has always seemed smaller than it should for such a large platform, especially given the volume of traffic we see from LinkedIn’s counterpart apps, which shows up under the referrer name

On January 20th, that changed when LinkedIn made a change to correctly attribute their traffic, some of which had previously been categorized as dark social. The impact of that change was immediate and significant.

Let’s look at traffic coming from to sites across the Chartbeat network over the last six months, we see two trends: a steady increase over the year, followed by a huge increase at the end of January.

Zooming in on the right side of the graph, January, 2016, we can see the immediate change in traffic as the attribution change was pushed:

linkedin_02_v3If we compare numbers from just after the change to the same time during previous weeks, traffic from was up by over 3x.

Some sites saw more than 6x increases in their LinkedIn traffic.

While LinkedIn still isn’t a major traffic source for many types of sites, we expect that many business-, media-, and technology-focused sites will see LinkedIn as a top-10 referrer going forward.

With Facebook’s change last year to help attribute all of their traffic, LinkedIn’s change here, and other work to come, we’re excited to see more traffic correctly attributed. We’ll continue to work with platforms in the coming months to bring their dark social traffic into the light.


2015 was a big year for top-quality journalism. Just looking at the 20 most read stories across the Chartbeat network, it’s clear that a heartening mix of longform reports and critical resources for breaking news captured and held the world’s attention this year. Quality content shone, even as the relationship between media and technology continued to shift – especially in the realms of mobile traffic, distribution platforms, and ad blocking.

In 2015, more than 70% of sites we measured saw traffic from mobile devices increase, and Facebook, as in prior years, generated the largest share of mobile traffic. In contrast to prior years, though, Facebook’s share of traffic itself was constant for most sites. That said, there’s no denying that the new channels for content distribution, like Instant Articles, Snapchat Discover, and Google AMP, will only grow in importance over 2016, presenting an opportunity for publishers to build their audiences. And this is the key. Even as some publishers, especially in Germany, are reporting high rates of ad blocking, by prioritizing audience, embracing new channels, and doubling down on speedy browsing we can build an even brighter media landscape for years to come.

So take some time to read Past/Forward. In it, we’ve proposed eight New Year’s resolutions for digital publishers seeking an outstanding 2016. We walk you through cutting down page load times, growing your loyal audience, writing winning headlines — pretty much everything future-focused publishers should strive for.

You can find Tony Haile’s forecast for 2016 and our eight digital media resolutions in Past/Forward.

When you work with as much data as we do—and trust me, it’s a lot—it’s humbling to show off the actual journalistic output we support. So, we’ve compiled a list of the 20 stories that held your attention longest in 2015 — for a grand total of 685,231,333 Engaged Minutes (or more than 1,300 years). These were stories that held you breathless. Enraged you. Inspired you. They were long-form reports, rich with narrative, like #1, 7, 11, and 17, which show that readers really do respond to quality (!!). They were live coverages of the attacks in Paris (#3, 4, 6) or the elections in Britain (#5). They were confessional essays and impassioned arguments, investigations and elegies. These are the stories that prove that digital storytelling isn’t just alive, it’s kicking ass.

1. What ISIS Really Wants

The Atlantic | February

2. The Science of Why No One Agrees on the Color of This Dress

Wired | February

In-depth examinations of global newsmakers topped the list in 2015. Undoubtedly, this was the year of long-form narrative.

3. Paris attacks: as they happened

BBC | November

4. Paris attacks: Bataclan and other assaults leave many dead

BBC | November

5. Election Live

BBC | May

6. Paris massacre: At least 128 killed in gunfire and blasts, French officials say

CNN | November

It goes without saying: Breaking news will always grab and hold attention.

7. Inside Amazon: Wrestling Big Ideas in a Bruising Workplace

The New York Times | August

8. Scott Weiland’s Family: ‘Don’t Glorify This Tragedy’

Rolling Stone | December

9. How One Stupid Tweet Blew Up Justine Sacco’s Life

The New York Times | February

10. Police: Bryce Williams fatally shoots self after killing journalists on air

CNN | August

11. The Lonely Death of George Bell

The New York Times | October

Honed craft. Timeless themes. Notice that these Times pieces are even more examples of the power of narrative journalism.

12. Spygate to Deflategate: Inside what split the NFL and Patriots apart

ESPN | September

13. At least 14 people killed in shooting in San Bernardino; suspect identified

CNN | December

14. The “Food Babe” Blogger is Full of Shit

Gawker | April

15. I Found An iPhone On the Ground and What I Found In Its Photo Gallery Terrified Me

Thought Catalog | April

16. No. 37: Big Wedding or Small?

The New York Times | January

Sometimes, the most engaging content is the most distracting. Readers will engage deeply with more than just serious news items.

17. Split Image

ESPN | May

18. This is Why NFL Star Greg Hardy Was Arrested for Assaulting His Ex-Girlfriend

Deadspin | November

19. The Coddling of the American Mind

The Atlantic | September

20. The Joke About Mrs. Ben Carson’s Appearance Is No Laughing Matter

The Root | September

Want to see how your stories stack up? Get in touch.

Update: a reader wrote in with the great suggestion of examining the effect of direct quotations in headlines. We found that headlines with direct quotes are 14% more likely to win headline tests than average headlines, making them the second most effective headline style we’ve tested. Please comment or get in touch with other suggestions for headline styles to examine!

Writing a catchy headline that captures the attention of your audiences is, without question, an art form. As demonstrated in this headline, blindly following guidelines can lead to copy that sounds cliché at best, and actively off-putting at worst. Still, effective headline writing can make quite a difference in the success of your content — after all readers have to get to the actual articles somehow — so it can be expensive to get wrong.

Chartbeat Engaged Headline Testing enables content creators and editors to become better headline writers. By testing copy in real time, newsrooms can challenge assumptions about what kinds of headline constructions work well and which don’t.

Accordingly, we would like to turn that introspective lens on some of our own recommendations of how best to use our tool and then on some commonly cited “tips and tricks” for getting the most out of your headlines. As a foreword, while we have the luxury of being able to plot general trends in a rich dataset of over 100 publishers and almost 10,000 headline tests, each publisher and audience is different. We encourage you to take a look at your own data and put some of our findings to the test (literally!) to see what works best for you.

Verifying Best Practices for Engaged Headline Testing

To help our clients get started with our tool, we often give them a list of best practices. Here are a few examples:

  • Test in Higher Traffic Positions
  • Don’t be Afraid to Test Multiple Variants
  • Test Distinct Differences

We like to encourage users to conduct headline tests that converge to a winner quickly, so that winning headlines spend the most possible time with the largest possible audience.

This begs the question of what “converging to a winner quickly” means, and to answer it, I would like to appeal to our data for an overall view. The graph below shows a histogram of experiments by the number of headline trials — that is, the number of unique visitors that see one of the tested headlines:


About half of conclusive experiments (those that determine a winner) need fewer than 2,500 trials to converge. More than 85% need fewer than 10,000 trials. That said, identifying an average convergence time for your site will depend on the amount of traffic you have and how “evergreen” your content is.

For sake of example, let’s imagine a publisher that gets 100 trials per minute. They want to see their experiments finish within 25 minutes. The above statistics imply that only about half of this publisher’s experiments will finish before we reach 25 * 100 = 2,500 trials.

Want to maximize the ROI of your headline testing practice? Learn how.

Click-Through Rate
Now, let’s take a look at how we can leverage higher traffic (click-through rate) positions to optimize for convergence time. The following graph is a density plot of number of trials needed for convergence against the CTR of the winning headline:


While there is a fair amount of noise in the plot, the main indication is that the needed number of trials is roughly inversely proportional to the CTR of the slot. So what does this mean in practice? If a publisher tests in a prominent headline position getting 8% CTR on the page, the test will converge in 4 times fewer trials than a position below the fold getting 2% CTR. That brings our convergence rate (within 25 minutes) from 50% to closer to 90%. Pretty astounding.

Number of Headline Variants
Finally, let’s graph the number of headline variants in each experiment:


Right now, we see that more than two-thirds of our headline tests are basic A/B tests, meaning only 2 variants. There are clear pros and cons for testing additional headline options. On the negative side, you need to actually write more headlines, and I can sympathize with the creative burden. (Unfortunately, taking the lazy way out in tweaking a word or rearranging a sentence tends to have less impact than trying to highlight different viewpoints or angles.) Also, adding an additional (average) headline often will hurt convergence time, because you need additional trials to explore the added headline.


But, as demonstrated in the table above, there is clear benefit to testing additional headlines as well. The above table shows the amount by which the winning headline exceeds an average headline, by number of headlines tested. The winning headline in a five variant experiment typically has more than a 50% higher CTR than the average headline, whereas you may only see a 23% benefit for a standard A/B test. This pattern of increasing divergence of winner to mean follows directly from the variance in the CTR of each headline. Another consideration is how often the original headline (Variant A) ends up as the winning headline. Admittedly, the following result depends fairly strongly on how organizations decide to come up with headlines; but even in the A/B headline case, publishers have been fairly significantly rewarded for using the additional variant. In some extreme cases, we have seen publishers use as many as 17 (!) different variants in a single headline test, successfully converging in fewer than 10,000 trials (!!).

Testing the Efficacy of Common Headline Themes

We wanted to take a closer look at the characteristics that make up a good headline. Some of the essence of a great headline, such as Vincent A. Musetto’s “Headless Body in Topless Bar,” can never be fully captured in categorical variables; but there are common tropes that are commonly used to capture audience attention. With the help of headline guides, other headline studies, and raw expertise, we compiled a list of 12 commonly-cited themes:

  1. Does the headline contain a question?
  2. Does the headline have a number?
  3. Does the headline use adjectives?
  4. Does the headline use question words (e.g., ‘who’, ‘what’, ‘where’, ‘why’)?
  5. Does the headline use demonstrative adjectives (e.g., ‘this’, ‘these’, ‘that’, ‘those’)?
  6. Does the headline use articles (e.g., ‘a’, ‘an’, ‘the’)?
  7. Is the headline in the 90th percentile of length (73 characters or greater)?
  8. Is the headline in the 10th percentile of length (32 characters or fewer)?
  9. Does the headline contain the name of a person?
  10. Does the headline contain any named entity (e.g., person, place, organization)?
  11. Does the headline use positive superlatives (‘best’, ‘always’)?
  12. Does the headline use negative superlatives (‘worst’, ‘never’)?

For this exercise, was used for the natural language processing tasks, including entity recognition and part-of-speech tagging for English language sites.

There are a number of statistical challenges in trying to sort out what characteristics have real significance and which are spurious outliers. The first thing to note when making multiple significance tests is that it is important to control the familywise error rate, via Bonferroni correction, or else you greatly increase the likelihood of spurious results. The second thing is that there are a number of confounding variables to consider. Raw CTR is appealing for its simplicity, but it could very well be the case that short headlines, for instance, are much more likely to be tested in leaderboard spots at the top of busy homepages, so despite being inferior to other headlines in the same spot, the CTR ends up being higher. This is a form of Simpson’s Paradox.

We will look at two alternate metrics of headline success. The first is scaled CTR, where instead of comparing CTRs globally, we look at the ratios of CTR of a given headline to the CTR of the headline that won the experiment. With this metric, the average scaled CTR of a headline is close to 77% in this data set, so we use that 77% as a benchmark to see whether a particular property has a beneficial effect.

The second metric is winner propensity. We look at the set of experiments that compare headlines with a given property to a headline without and calculate how often we would expect headlines with that property to win, if winners for each experiment were chosen randomly. We then see whether the headlines of the given property are more likely to win.


The results were somewhat mixed. Only long headlines and headlines with demonstrative adjectives show significantly higher scaled CTR, and only headlines with demonstrative adjectives and numbers show higher propensity of being declared winner in a given headline test. The presence of articles actually significantly detracts from scaled CTR.

It’s worth discussing the one unambiguous result in a bit more detail. Demonstrative adjectives can actually be used in multiple ways in a headline. You can use them to create intrigue in clickbait-ish fashion: “These simple tricks will leave you speechless” or “You’ve never tasted anything like this.” There are also quite a few examples in our dataset of using demonstrative adjectives as a temporal specifier: “GOP Debate this evening,” for instance. In the future, as we collect more data, we can think about drilling down more granularly into specific constructions.

Perhaps more interesting than the positive results is the lack of significance among other factors that have been cited to be useful in capturing the attention of an audience. “Use terse, punchy headlines”; “Ask questions”; “Name drop.” None of these properties show much predictive power in the general case.

“That’s right, writers: We’ve proven that ‘5 Ways To Write The Best Headline Ever’ isn’t actually that effective.”

Final Thoughts
So where does that leave us? If you want to be an effective headline writer, maybe there is no substitute for creativity and attention. Watch for patterns in the headlines that end up floating to the top. Take the time to discuss what worked and what didn’t. Avoid the formulas and cliches. Be liberal with your use of headline testing, so that you can harness feedback from your readers in real time.

If there are any other ideas that you would like us to take a look at in the data, especially as our repository of tests grows, please don’t hesitate to reach out.

In the meantime, here’s a great resource for headline testing optimization.