June 11, 2008

How much linguisitic sophistication is needed in Voice of the Customer/Market applications?

According to Attensity CTO David Bean:

I’m guessing most text mining vendors would agree with those views, although they might not agree with his elaborations, which include:

So the question arises: Just how much linguistic sophistication is needed in these market-trend-oriented text mining applications?

I actually got onto this subject not just because of what David said, but also via a conversation an hour earlier with Brooke Aker of Expert System, who proposed linguistic sophistication as a key reason for beating the competition (which, however, didn’t include Attensity or Clarabridge) at two accounts. The point Brooke was stressing is that it’s important to be able to extract multiple facts or indicators of sentiment from the same sentence. E.g., “I just had a crummy Chevy, but at least the seats were comfortable” is both a negative indicator about Chevrolet and a positive indicator about Chevrolet’s seats. Attensity captures both of those too, and I think Clarabridge would as well. (If you do comprehensive/ exhaustive extraction, you extract — well, you should extract comprehensively.)

Anyhow, my first-best answer to the question I posed is:

But what do you think?

Comments

One Response to “How much linguisitic sophistication is needed in Voice of the Customer/Market applications?”

  1. Manya Mayes on June 11th, 2008 4:28 pm

    Linguistic sophistication is important in lieu of understanding the voice of the customer first hand. Understanding the agents take on a call is not the same as understanding what the customer said care of a voice recording. Additionally, if a customer phones a bank asking the agent to “correct a mistake on a bank statement or I will close my account”, this doesn’t necessarily mean he will actually close his account. Maybe he (or she) is a habitual complainer and knows how to press buttons to get things done.

    The voice of the customer software that most vendors offer is not actual voice but more sentiment analysis of the agent’s keyboard entered summary of the call. The linguistic software is trying to infer the customer’s voice from this agent information.

    Last year at the text summit, I made a small sideways comment about SAS being the only vendor actively analyzing actual voice. Currently, almost all of my presales support is in the area of voice analysis where I present the extension of work mentioned above into BI reporting software for consumption across an organization.

    Voice of the customer is suddenly becoming very hot. It’s not all talk. Well, actually voice is talk, so maybe I should say it IS all talk ;-) While I’ve been speaking about voice analysis for some time, it has only recently gained good traction. Maybe other vendors messaging around “voice” of the customer is not meeting customer expectations of the software. It is certainly helping us.

    And, of course, nothing surpasses having the customer personally rate their experience and mining the resulting information.

    Manya Mayes
    Chief Text Mining Strategist
    SAS

Leave a Reply




Feed including blog about text analytics, text mining, and text search Subscribe to the Monash Research feed via RSS or email:

Login

Search our blogs and white papers

Monash Research blogs

User consulting

Building a short list? Refining your strategic plan? We can help.

Vendor advisory

We tell vendors what's happening -- and, more important, what they should do about it.

Monash Research highlights

Learn about white papers, webcasts, and blog highlights, by RSS or email.