AlchemyAPI has been growing at an amazing pace over the past year since our first public release.  We’re processing a massive number of API calls each day, for a variety of customers in multiple industry verticals.

We love engaging with our customers and user community, gathering feedback regarding our service and suggestions for improvement.  This community feedback has a direct impact on our product planning and the general direction of AlchemyAPI.

This new AlchemyAPI release brings a new feature requested by a number of you in our community:

Relevancy Ranking

Relevancy ranking expands upon AlchemyAPI’s sophisticated named entity extraction capability, applying a numeric ‘relevancy score’ to every item we detect.  These scores convey the importance of a given entity (Person, Company, etc.) to the document being processed as a whole.

Relevancy ranking enables one to easily sift through the named entities within a given news article or other piece of content, identifying what’s important and what isn’t.

Our relevancy functionality employs a sophisticated statistical ranking algorithm, employing over two-dozen different signals & cues, as well as advanced probability modeling. It provides far superior results to frequency/count-based relevancy ranking approaches.

This AlchemyAPI release also offers increased named entity extraction precision. This means fewer false positives and better extraction results.  Give our system a whirl and you’ll find it’s among the most accurate in the industry!

Stay tuned for more updates!