Follow

Content source ranking: Automatic based on engagement data

Automated ranking based on engagement data 

The average paper pulls in over a 1000 articles, videos, photos per edition.  Out of all that content, how does paper.li decide which articles to present on a paper? 

In order to unearth a good mix of engaging content based on all your sources, automated ranking evaluates articles against each other across all sources depending on engagement data.

For each type of source (Paper.li Genius Source, Twitter, Google +, RSS feed etc) we've defined a set of social signals used to evaluate the "importance" of a shared article.  The scoring of articles is based on three main elements:

  • who shared the article
  • who published the article:  we attribute reputation scores to article sources, based on the monthly processing of 240 million articles
  • the content of the article itself: we look at the article itself, taking into account when it was published, the language, topic covered. 
 
In order to unearth those content gems from your entire list of sources, we then aggregate and rank articles across sources, and include some "boost factors" depending on the type of source (e.g. single Twitter user, RSS feed, twitter keyword search, etc) to end up with a ranked list of articles based on engagement data across your entire list of sources.
 
Pin a source to give it a boost   (Screen shot 2010-12-22 at 09.38.05.pngPro)
 
If you have a source with content that you want to include in your paper, regardless its engagement ranking, pin it!
 
To pin a source, go to your Paper Settings Dashboard > Content > View your content sources > click ... to the right of the source you would like to pin.  
 
A pinned source is placed at the top of your source list.
 
 
Your final, ranked list of content presented on your paper populates the headlines and section pages of the paper, resulting in content that is sure to be more variedrelevant and engaging for you and your readers.
 
 
 
Amount of content fetched

We go back and fetch all tweets and content specified in your content sources, discard any duplicate URLs, URLs from private accounts or links that are broken, then analyze, organize and present the most relevant content (based on the top--max. 6--most relevant topics), video and photo excluded. To keep discovery relevant, we limit content to 250 articles, 100 images and 50 videos per paper. 

 
 
Switching from Automated to Manual Ranking (Screen shot 2010-12-22 at 09.38.05.pngPro)
 

If automated ranking is not working for you, you can change your ranking method to manual ranking, where you determine the source ranking yourself.  From your Paper Settings Dashboard, chose Content > Advanced Settings. Use the toggle to turn on manual ranking.

 
We'd love to know what you think. Be sure to drop us a line and let us know your thoughts.
 
Last edited: Julia Yaziji March 4, 2016
 
Was this article helpful?
1 out of 1 found this helpful
Have more questions? Submit a request

Comments

Powered by Zendesk