Content recommendations

The Content Recommendations toolbar plugin adds a capability to the toolbar of the content editor that allows you to insert content placements, dependent on having set up a Content Collector Connection. Click on the icon to insert a content placement based on an algorithm of your choosing at the place of the cursor. 

To add a recommendations placement, edit an interaction and click "Insert object" from the content editor toolbar:

Screen_Shot_2017-05-11_at_6.54.23_AM.png

Selecting 'Content Recommendations' will add a placeholder placement to the content editor. Hovering over the placeholder will light it up in blue. Click and edit or double click the placeholder to open a configuration popup with four tabs for configuring the content placement:

Source

Select a source of content, which is defined by configuring a Content Collector Connection.

Design

Template
Select another template for your recommendations placement, or edit your own template
Number of items
Enter the number of articles/posts you'd like to include in the content placement
CSS URL
If you wish to control the styling of the placement by loading CSS from an accessible URL, enter it here.
Custom CSS
Optionally enter custom CSS to style the list. This CSS will overrule CSS loaded from the URL, and the CSS in the template.

Algorithms

On the algorithms tab, you will be able to affect the algorithm that selects content for each individual user. As you make changes here, you should be able to see them reflected in the content placement in your editor window:

There are a number of algorithms you can introduce, to boost the prevalence of articles with certain characteristics as described below. For each algorithm added, you can control whether it is used at all, or to what degree it will be incorporated into the overall content selection.

The algorithm options can be grouped into three types: Aggregate stats-based, content-based, and profile-based. 

Aggregate stats-based algorithms

Recent high CTRs: Content that has been clicked within content recommendations placements served by BlueConic.

Breaking news: Content that has been read the most across the site over the last several hours.

Viral news: Content that has been popular as an entry point to the site over the last several hours.

 

Content-based algorithms

Look-alike articles: Content that has a similar textual makeup to the current article being read.

Same category: Content that is in the same category as the current article being read.

Recency: Content that has a recent published date. 

 

Profile-based algorithms

Collaborative filtering: Content read by other users similar to the current user.

Same interest: Content that is in the same categories as those the user has shown the most interest in.

Profile-based algorithms also take a "ramp up speed" setting, which allows BlueConic to react more quickly to any information that is being populated in the user profile:

Filters

The filters area allows you to include or exclude content based on its metadata or other options. 

Show articles from the same category: Only include articles from the same category as the current article (only works with content placements on article pages)

Hide read articles: Exclude articles read by the current user.

Frequency cap: Exclude articles after the user has not clicked on them after having clicked other articles within the same placement a specified number of times.

 

The Content Recommendations plugin is a certified plugin. Contact us if you are interested in using content recommendations.