SAS Inc offer a product name 'SAS Sentiment Analysis' which was an acquisition of a company called 'Teragram Corporation'.
This product won the Business Wire product of the year award for its excellence in innovation. Below is an extract of from the press release, which describes the SAS Sentiment Analysis feature set / benefits which sound very similar to what the Metavana patent details:
SAS Sentiment Analysis’ high-performance crawler locates and extracts sentiment from digital content sources, including mainstream websites, social media outlets, internal servers and incoming news feeds.
In terms of how the crawled content is processed to locate sentiment it states:
SAS’ unique hybrid approach combines powerful statistical techniques with linguistics rules to improve accuracy to the detailed feature level. It summarizes the sentiment expressed in all available text collections – identifying trends and creating graphical reports that describe the expressed feelings of consumers, partners, employees and competitors in real time.
The above description makes the products sentiment analysis capabilities seem more advanced than the categories and keyword approach detailed in the patent application.
I researched further to see if I could find more information on the SAS product related to categories and keywords as a method to locate sentiment and found:
- a post on the SAS blog called 'Predicting American Idol results based on Twitter sentiment' which details that keywords can be used. The post it states:
Generating the scores was easy enough with SAS Sentiment Analysis. I used a SAS macro to copy two weeks of Tweets about the final six contestants. From there, I took an existing Sentiment project (about an actual business), and copied over the list of generic positive and negative keywords. I ran the model and then added in a few extra rules to account for the nuances of Twitter-speak (turns out most Twitter-speak consists of shortenings of "love" and "sucks").
- an article titled 'SAS Text Analytics and Teragram', which refers to the 'Content Categorization function' as described below:
Another important point is that SAS Text Analytics includes four components. There is the SAS Enterprise Content Categorization function. The system parses content and identifies entities. Metadata are created along with category rules. The second function is SAS Sentiment Analysis. A number of companies are competing in this sector. The SAS approach sucks in emails, tweets, and other documents. The system identifies various subjective shades in the source content.
I don't know the SAS product intimately but it very much appears to perform everything described in the patent application. The sources I have used are not perfect and they describe the SAS product from the user point of view as opposed to an informed objective one.
It actually looks like the SAS is far more advanced than what the patent describes which appears quite rudimentary.
One thing to note: I couldn't find any SAS or Teragram patents to usesuse as sources.
Business Wire Press Release July 26, 2010
SAS Blog describing keywords as a component of locating sentiment May 12, 2011
Article describing categories as a component of locating sentiment May 28, 2010