The Concept Insights service will be deprecated on August 12, 2016, after which no new instances of the service can be created. AlchemyLanguage's concept function can be used as a replacement for most Concept Insights use cases; therefore, we encourage existing Concept Insights service users to migrate to AlchemyLanguage. AlchemyLanguage provides multiple text analysis methods, and works with Watson Knowledge Studio to enable you to train custom models for a specific domain. You can then use that model with the AlchemyLanguage methods. See the AlchemyLanguage documentation on customization for more information.
The IBM Watson™ Concept Insights service provides Application Programming Interfaces (APIs) that enable you to work with concepts and identify conceptual associations in the content that you provide as input to the service. Input content is auto-tagged against a concept graph, which is a formal representation of the relationships between concepts that are present in the data on which it is based. The concept graph used by the Concept Insights service is based on content that has been ingested from the English language Wikipedia.
You can see a quick demo of the Concept Insights service in action. The demo application enables you to locate relevant TED (Technology, Entertainment, and Design) talks using topics, words, or concepts. This demo uses publicly a corpus that was created from publicly available TED talks.
We are always looking to improve and learn from your experience with our services. You can submit comments or ask questions about Concept Insights in the Watson forum. You can also read posts about Watson services that are written by IBM researchers, developers, and other experts on the Watson blog.
This is a GA release of the Concept Insights service. If you were previously using the beta version of the Concept Insights Service, and you would like to continue using the service, see Upgrading from Beta.
To begin working with the Concept Insights service by creating and running applications that communicate with the service, see the following:
To create and run an example Node.js application that works with the service from the command line, see Watson Quick Start for Node.js.
To create and run a sample Node.js application that works with the
service from a web browser, see Developing a Watson application in Node.js.
You need the link to the source code for the Node.js application at the concept-insights-nodejs
repository in the
watson-developer-cloud namespace on GitHub.
For the sample application available from GitHub, you can download a
.zip file that contains the source code or, if you are
familiar with Git, fork the repository into your Git namespace or clone
it to your local system. To learn about Git or to download Git for your
operating system, see git-scm.com/documentation.
For a language-independent introduction to working with Watson Developer Cloud services and Bluemix, see Developing Watson applications with Bluemix. That page provides an overview of working with Watson services with the Bluemix web interface, the Eclipse IDE, or the Cloud Foundry command-line tool.
See the following for more information about the Concept Insights service: