Harnessing the power of storytelling to change the world™ vs. YouTube

Posted on April 4th, 2011 by Keith Laidlaw

Jarek Wilkiewicz from the YouTube API Team discusses in his blog post about building video apps: Man vs. Machine: Curating with YouTube APIs. He says that as well as empowering users to organize video content themselves, another approach is “a hybrid of curator’s selections and related content recommended by an algorithm.”

To achieve this, by Link TV, a non-profit committed to improving the world with storytelling, utilizes semantic analysis … Top-level categories are decided upon (or “bootstrapped”) by curators, however, while navigating the site users are presented with automated recommendations as well.

Read the full post here

Social Actions API Enhancements

Posted on January 21st, 2011 by Rob DiCiuccio

We’re happy to announce that is among the first to utilize the latest version of the Social Actions API. The updated API includes several enhancements, such as semantic content analysis, term boosting, and the ability to query by and return Linked Data entities.

From yesterday’s announcement:

The updates introduce Semantic Analysis and Natural Language Processing (NLP) capabilities to the Social Actions API and begin to connect Social Actions to the wider Linked Open Data community.
Link TV, in prototyping their ViewChange platform, noticed that the Social Actions API wasn’t producing the best possible results. They invited us to explore with them what would be involved in updating our platform so that ViewChange could feature more relevant results.
Link TV, along with Doug Puchalski and Rob DiCiuccio of Definition, helped us articulate the changes that would need to occur and then connected us with a funder who could underwrite what amounted to a very significant enhancement to our code base. In one month, we had approximately as large an investment in the technology as we’d had in total up until that point.
The Social Actions API now cross-references issues and locations with universal identifiers that have been assigned to them. Just like you might cross-reference the subject of a book with a Dewey Decimal number, we are now cross-referencing each action with a universal identifier that helps to link it to related data. Using Zemanta, we are able to provide URIs (Uniform Resource Identifier) from Freebase and DBPedia that make the connection between actions in our system and other material on the web that relates to the same topic.

The ability to query using Linked Data URIs (e.g. removes the ambiguity inherent with a traditional keyword query (“John Adams”), which could be interpreted as any number of persons, such as the former U.S. President or the composer.

We hope that, through this enhanced integration between Social Actions and, we are able to help you get involved by bringing you relevant, timely actions, so you can make a difference.

Read the entire interview with Peter Dietz from Social Actions.

Entity Extraction & Content API Evaluation

Posted on May 18th, 2010 by Rob DiCiuccio

The platform utilizes several third-party APIs to perform semantic content analysis and related content aggregation. The technologies developed by these partners have allowed us to leverage powerful tools for entity extraction and content discovery, and facilitate integration with the emerging Semantic Web. These tools allow us to focus more of our efforts on creating an engaging user experience, as well as building new open source tools for content curation, without duplicating the efforts of others.

There are several open APIs that provide semantic analysis and content discovery services. The following evaluation was conducted in February 2010, in order to assess the available APIs and their compatibility with the needs of the platform. The API tests were performed using a custom PHP application for querying and displaying API results. If you would like the source for the test application, send me a message.
Read the rest of this entry »