New Content Analysis API

Today we're pleased to announce the availability of our new Content Analysis service through YQL. Content Analysis replaces Yahoo!’s popular Term Extraction service and now provides advanced content analysis on either text or a URL, leverages Yahoo!’s state of the art MLR technology to extract key terms from the content, and, more importantly, to rank them based on their overall importance to the content.

The Content Analysis Web Service detects entities/concepts, categories, and relationships within unstructured content. It ranks those detected entities/concepts by their overall relevance, resolves those if possible into Wikipedia pages, and annotates tags with relevant meta-data. For developers who publish unstructured data, Content Analysis adds substantial value by giving you a ranked vector for each document you send to the service. Armed with the key terms for each unstructured document, you can more effectively describe these pages for SEO and other indexing needs. In addition, by resolving terms to Wikipedia entities, Content Analysis allows you to connect you documents to the most robust knowledge stores powering the semantic Web. Last, with each document mapped to one or more nodes in our Yahoo! Content Taxonomy, you can create new structures for your sites which effectively group documents into all appropriate content nodes. In all, Content Analysis provides you with a robust summary of each document or URL you send to the service including key entities and key contextual terms

Please give our content analysis service a try and start enriching your content today.

We will continue to support the Term Extraction requests, but calls must be directed to our YQL table since we’ll be shutting down the non-YQL service on March 31st, 2012. The new features and MLR are supported only in the new request format.

Check out our blog post on the Y! Search blog for additional details.