Commentary
2/8/2007
10:37 AM
Seth Grimes
Seth Grimes
Commentary
Connect Directly
Twitter
RSS
E-Mail

Defining Text Analytics

I've been writing and speaking on text analytics for years. This work led to a recent call from Philip Russom, an analyst at The Data Warehousing Institute, who invited me to contribute my take on text analytics, in six sentences or fewer, for a forthcoming report on the subject. I failed. I took eight sentences, but I thought I'd share the lot with you.



I've been writing and speaking and consulting on text analytics for years. This work led to a recent call from Philip Russom, an analyst at the Data Warehousing Institute, late of Forrester, Giga, Hurwitz, and Intelligent Enterprise. Philip invited me to contribute an expert comment - my take on "text analytics" in six sentences or fewer - for a forthcoming TDWI report on BI search and text analytics.

I failed. I took eight sentences - we'll see if Philip cuts them down - and I thought I'd share the lot with you.Text analytics is technology and process both, a mechanism for knowledge discovery applied to documents, a means of finding value in text.

Solutions mine documents and other forms of 'unstructured' data. They analyze linguistic structure and apply statistical and machine-learning techniques to discern entities (names, dates, places, terms) and their attributes as well as relationships, concepts, and even sentiments. They extract these 'features' to databases for further analysis and automate classification and processing of source documents. They exploit visualization for exploratory analysis of discovered information.

Text analytics goes beyond search to turn documents into data. It extends Business Intelligence (BI) and data mining and brings analytical power to content management. Together, these complementary technologies have the potential to turn knowledge management into knowledge analytics.

Does this capture the matter? I fear my definition is a bit grandiose. That would reflect my enthusiasm for text analytics. The technology, broadly or narrowly defined and still in an early adoption phase, has demonstrated potential to add value to many, diverse applications. Let me know your take. And if you're a text-analytics researcher or vendor or practitioner, send me your predictions of "what's next for text" for a white paper I'm writing for the 2007 instance of the Text Analytics Summit that I chair. (Top of my list is Question Answering, which I wrote about in a Breakthrough Analysis column last year.)

Text analytics is about making human communications comprehensible to computers. However the field does develop, I know it will remain intriguing, a rewarding IT discipline to be involved in.

Technorati ProfileI've been writing and speaking on text analytics for years. This work led to a recent call from Philip Russom, an analyst at The Data Warehousing Institute, who invited me to contribute my take on text analytics, in six sentences or fewer, for a forthcoming report on the subject. I failed. I took eight sentences, but I thought I'd share the lot with you.

We welcome your comments on this topic on our social media channels, or [contact us directly] with questions about the site.
Comment  | 
Email This  | 
Print  | 
RSS
More Insights
Copyright © 2021 UBM Electronics, A UBM company, All rights reserved. Privacy Policy | Terms of Service