What to investigate with Google Discover API — Some ideas to start with

How to access the API

Official Documentation:

Python Example :

Javascript Example:

What to investigate

Some first things I investigated. Happy to learn about your ideas…

Section performance

Compare which sections work best for you. An interesting additional metric might be the days the articles where ranking on average in Discover:

Author performance

Learn about the authors in your Newsroom. Who is doing best to optimize CTR?

Article Features

How does having a sildeshow and a liveticker in an article affect Discover performance compared to any other combination

Recent articles vs. section average, feature average, author average

Compare the recent article vs. the performance in the past to detect outlier articles (in terms of e.g. really good CTR) for every category. What can you expect from an article in your “economy” section?

With Named Entity Detection

If you extract with some named entity detection tool the entities, which describe the article you could do something like this.

Best topic/entity for ranking days in Google Discover

or impression, or clicks, or CTR, ….

Entity + section performance vs. section in the past

Here I grouped recent entities + sections and compared versus the sections performance in the past. If entities were appearing in multiple sections there are multiple lines.

Single (person) entities vs. their past performance

Here the before grouped (person, location, organisation, …) entities are splited into single rows. This makes it much more likely that this entity was there in the past. If you want to compare entity now vs. entity in the past this works much better.

--

--

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store