Making Queries better with related phases

Posted by Marshall Sponder on December 03, 2010 | Link It

In my the last few weeks I have been hearing of ways to improve the results of Social Media queries by finding out words that often appear near each other in documents that are crawled and indexed.  While some platforms don’t allow that information to be extracted, others do, including Sysomos.

I wanted to be sure Sysomos did, in fact, do this (provide the numerical association number between any two commonly associated words in a topic, and you know what?  It does (see the spreadsheet excerpt below the buzzmap).

Here’s an expanded “buzzmap” on the keyphase “Influence” that Sysomos produces.  But what you don’t know is that it can also take that information in “plain form” and then exported to .csv and provide a better query.  I’ll go into what makes this the raw material for a much better query in a subsequent post – but just keep this in mind.

I used such a wide word that I think there’s still a lot of things that could be refined before getting to this stage – but it’s possible to make much better queries with this information.



Post comment as twitter logo facebook logo
Sort: Newest | Oldest




UPCOMING SPEAKING

The inaugural Social Media Analytics Summit is the first ever two-day business conference with a complete focus on social media analytics. Social media analytics enhances customer service, improves brand and reputation management, and measures overall social media success for businesses