The 2009 Text Analytics Conference was a great time, congratulations to the organizers for once again putting on a terrific event. I heard from one of them that attendance was down 20% from last year, which sounds about right given the economic situation and travel budgets right now, but it didn’t put a damper on the festivities.
Voice of the customer was once again the application that got the most play, from vendors and speakers. However reputation analysis/opinion mining/buzz monitoring – or what was sometimes called social media analysis – was a close second this year, with an eye to the lower-cost offerings springing up in this area to mine blogs and internet forums. Some related points:
Twitter came up several times (it’s everywhere this year of course), but prevailing opinion was that it’s not a great resource for text mining – too many misspellings, abbreviations, and just plain not enough text per tweet to be able to get a good read on the content.
Facebook’s Roddy Lindsay was back to offer an overview of some of the projects underway to mine popular topics on the site for insight on its users and how their age, gender and regional demographics affect their views. Unfortunately as data on Facebook is private to its users and their network of friends, this was kind of a tease for those of us who would love a bigger peek at it.
End users were well-represented this year, and I was even fortunate enough to get to moderate the end user panel, featuring former school superintendent Chris Bowman, Mike House of Maritz Research, Bryan Jeppsen of JetBlue, John Lehto of Monster and Rick Lewis of AOL. The gentlemen weighed in on everything from technical problems (they overwhelmingly chose SaaS to avoid issues) to variations on the inevitable ROI question, and provided some much-needed perspective to what end users expect out of the vendors and their products. Response has been good, and for anyone wanting more, be aware that the ever-quotable Mr. Bowman is now on Twitter and may very well be watching your every move.