Case Study: Find Quotes

http://demos.kudosknowledge.com/findQuotes

API Application Example

As an example implementation of using our Semantic API, we made an application that finds quotes that relate in meaning to the text you enter. In terms of our API, the content collection is a quote database, which is uploaded into the semantic word space. The user then enters text into the query field and when they hit ‘Get Quote’ the application simply returns quotes like the text you’ve entered. In this case the demo application only does one comparison, that being ‘find similar content’ to this. In contrast our API can handle multiple queries on the content.

Case Study: Enliten

www.enliten.com

Enliten’s Social Intelligence Technology: Intelligent Semantic Filtering

Enliten brings Semantic Social Intelligence^TM technology to any content, feed, or information source with powerful information aggregation, to bring quality filtered relevant information that eradicates information overload.

Enliten uses social intelligence to take note of what your interested in and what your not, and it then uses intelligent semantic filtering to adapt and improve your information views, even as your interests evolve. Because information interests inside Enliten are organised into channels, each channel understands the particular interests of that channel, thus allowing for the variety of interests we surely have .

Using an intelligent semantic learning engine, each channel continually learns and adapts from your interaction with it to become ever increasingly relevant. The result is 100% targeted relevant information with all the noise pollution eliminated.

For example, if you have created a channel with the topic “Skype” but your interested in Skype for phone and not so interested in Skype and Microsoft’s buy out, then you can tell Enliten your interested in the former and not the latter by using the thumbs up and down buttons on relevant articles. The channel on ‘Skype’ will now get semantically oriented to your particular interests on the subject, even as your interests change.

And its not doing this with keywords, but its analysing the overall meaning of the article you are interested in, as well as the one your not. Now each time a new article comes in it can be semantically mapped to your interests to see how relevant it is!

Read more about Enliten on our product page.

Case Study: CelebTweety

poc.celebtweety.com

Semantic Social Intelligence^TM has a way of inferring and attributing meaning to unstructured data. It is particularly useful for finding meaning inside data or relationships between information.

An example of this in a very simple implementation is CelebTweety Proof of Concept Project. The content collection is every single celebrity tweet ever tweeted expressed as a multidimensional semantic word space. The user’s content is their own tweets or Facebook updates mapped into the semantic word space. Now we can discover hidden relationships between the users data and celebrities’ data. The simplest of this would be: those celebrities who are closest to you in word space will be those who talk about the same things as you. And this is exactly what CelebTweety does: It analyses the meaning behind your tweets or Facebook posts and compares them to every single celebrity tweet. It then tells you which celebrity you are most like.

CelebTweety POC was a proof of concept project to test our newly invented Semantic Social Intelligence^TM technology.

Read more about CelebTweety POC on our product page.