Twitter is a repository of potential customer interactions. Often times these interactions stop at routine customer experience. However, by using natural language processing, like that present in Salience, the potential for more actionable interactions increases. Such technology allows companies to determine what a customer—or an entire customer base—is likely to do, whether its buy, sell, recommend or quit a product or brand.
Take a simple [tweet] like… ‘I’ve been saving like crazy for Black Friday. iPhone 6 here I come!’ Said Jeff Catlin, CEO of Lexalytics, to Information Week.
There are no words like ‘buy’ or ‘purchase’ in this tweet, even though their intention is to purchase an iPhone, continued Catlin. However, Lexalytics is still able to determine what is going on as well as who and what it involves. It does this by determining the intendee, the intention and the intended object. In this case, it would look like this:
Intended Object: iPhone 6
Lexalytics is able to understand this intent because of something called
grammar parsing technology.
Intention is kind of the sexy feature, but the grammar parser is the key that makes it go, the ability to understand what people are talking about, regardless of content type, said Catlin.
We’ve built a grammar-parser for Twitter, which deals with the fact that there’s bad punctuation, weird capitalization, and things like that. Another cool aspect of this intent analysis is it can be run on millions of tweets in only seconds. This helps companies determine customer’s buying habits.
But interest does always come back to the application of intention analysis in law enforcement.
If you’re the government and worried about terrorism, you can mine Twitter streams and look for harm, continued Catlin.
Is there an intention to do harm here? That’s a really interesting example. I consider it scary, but also very interesting.