Comments on: How much linguisitic sophistication is needed in Voice of the Customer/Market applications? http://www.texttechnologies.com/2008/06/11/linguisitics-voice-customer-market/ Understanding technology ... in both senses of the phrase Thu, 19 Jan 2012 17:11:01 +0000 hourly 1 http://wordpress.org/?v=3.0.3 By: Manya Mayes http://www.texttechnologies.com/2008/06/11/linguisitics-voice-customer-market/#comment-42520 Manya Mayes Wed, 11 Jun 2008 20:28:31 +0000 http://www.texttechnologies.com/?p=238#comment-42520 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 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

]]>