Big news from Content Insights: on the 24th of June, the new and improved platform was released.
For those who may not know, Content Insights is an advanced content analytics solution capable of measuring real reader behavior and content performance with unrivaled precision. It runs on a complex algorithm called Content Performance Indicator (CPI) that recognizes three different behavioral models: exposure, engagement, and loyalty.
The CPI algorithm is continuously improved thanks to the close guidance of our product developers, visionaries, data scientists and data engineers, mathematicians, and of course – existing clients who provide their precious feedback and participate in creating the product they want and need.
In addition, the company has experienced editors in its ranks, which helps the whole team fully understand the pain points of publishers, newsrooms, media organizations, and content professionals, and more importantly – to clearly see what value they seek and expect to get from data.
As a consequence of this collective effort, Content Insights released a new, improved platform with the following changes:
- New CPI calculation
- Unique segmentation
- Updated topic analysis
- New Account & Organization management
- Improved platform performance
1. New CPI calculation
The CPI algorithm recently reached its third, most precise version yet, and we also introduced important changes in the way things get calculated. This new CPI calculation was necessary to enable proper segmentation and it brought more precise insights for users. Before we move on to explaining these changes, we’re just going to run through the basics and help you better understand CPI scores and why they matter. CPI scores for all three behavioral models (exposure, engagement, loyalty) are always presented in a number between 0 and 1000. Interpreting them is pretty straightforward:- CPI score of 500 = baseline
- CPI score < 500 = underperforming
- CPI score > 900 = exceptional performance
What changed?
In the past, CPI values for all dimensions (articles, authors, topics, sections) were calculated as the average value of an article’s CPI for the observed dimensions in the selected time period. Now, summary metrics values of the observed dimension are compared (benchmarked) with the summary metrics values of the other dimensions of the same type. In the past, we compared articles published in the last 30 days to pre-calculate the CPI. Now, CPI is calculated on-the-fly and ad hoc, for whichever period is selected.Why does this matter?
The change in the way CPI is calculated was necessary to enable proper segmentation, which is a new feature within the platform. In addition, this new calculation is more beneficial for users as it delivers more precise insights compared to the previous platform, enabling them to make better strategic decisions empowered by more relevant insights.2. Unique segmentation
Segmentation is commonly found in analytics solutions. By creating different segments, you can isolate and analyze various subsets of data and enjoy a more granular view. For instance, it is possible to assess the performance of a specific referrer and better understand how and where your audience likes to consume your content. But, here’s what makes the segmentation feature in Content Insights unique.What changed?
Within the previous Content Insights platform, users could only apply meta filters to switch views and see metrics and CPI values for selected dimensions (sections, topics, authors, articles). The new platform is enriched with unique segmentation which enables users to use traffic filters as well (device type, reader type, channel, campaign, referrer, referrer type). Filters can be saved on the domain level or user level and custom segments can be created, and this flexibility is something our clients really appreciate.Why does this matter?
The reason why our segmentation capability is unique lies in the fact we recalculate the CPI values incredibly fast for each segment users create. This means that you will not just discover the amount of traffic coming from, let’s say, Facebook, but the actual quality of that traffic in terms of engagement, exposure, and loyalty. And all that in just a few clicks. You can segment your traffic in the following ways:- Reader Type: Subscribed / Anonymous / Registered
- Article Type: Free / Premium / Preview
- Channel: AMP / FIA / Native Mobile
- Referrer Type