Archive for November, 2013

Photo Courtesy of Greg Younger

We all know sentiment analysis is useful for customer feedback. We know it’s important for social media monitoring, and customer experience management. We know it can be used for market research, and survey coding, and all the usual big business use cases that deal with lots of text and need it analyzed fast.

What I’m curious about, and what’s surprised me most in the years I’ve been working with this technology, are the unusual applications most people don’t even think about.

Here are three of the coolest use cases I’ve come across in the last year.

Keep Reading →


It’s always interesting to explain sentiment from a text or speech analytics standpoint to someone who has never heard of it before. Sometimes “emotion detection” is used, but everything has emotion, right? Right!? RIGHT! There are subtle differences in how we write and how we speak that make sentiment analysis particularly tricky.

First off, I’ll admit, it’s not very accurate from a numbers perspective. Today the technology just isn’t there to have 100% accuracy. But what does that even mean, 100% accuracy? Are humans 100% accurate? Think of the last time you got the wrong order at the drive thru. Sentiment is a subjective exercise at best and depending on cultural and geographic differences it can be a total guess at worst. Keep Reading →