In my previous EIM framework post, I covered how:
- Text data processing must be part of every EIM framework within an IT organization
- The rise in prominence of text analytics can be attributed to Web/social data and well-defined use cases on employing text data processing to unravel golden information nuggets within that data
- Organizations need to think beyond established patterns for using text analytics in broader implications
In this post, I’ll examine use cases that yielded significant returns to the organizations that tried this approach.
Text Data Processing: a Different Animal
Unlike structured data, which comes in the form of tables and columns, text data comes in a relatively unstructured format with significantly more information – which must be parsed before it’s actionable – and a higher noise-to-information ratio.
It’s important that businesses gain exposure and experience organizing, processing, and analyzing text data from an analytics prospective. IT organizations must also:
- Learn and manage new technologies (such as content aggregators) and context (text data quality)
- Determine what sources to watch, how to clean sources, and whether to keep access to summaries or full text, etc.
Many of these actions and decisions likely didn’t come up when dealing with structured content.
Analyzing Customer Feedback on Forums and E-mails = Cost Savings
For Intuit Inc., maker of the popular TurboTax software, customer feedback that was once hidden amidst a flood of customer emails, comments, and forum responses ultimately saved the company millions of dollars when it implemented text analytics.
By analyzing the text in customer feedback forms, Intuit determined that customers weren’t satisfied with its website functionality. A significant number of them had trouble finding the Frequently Asked Questions page on one of Intuit’s websites – a section buried about five levels deep. Some adjustments to the navigation window resulted in a 50-percent increase in user self service. As a result, call volume to Intuit’s support call center shrank, saving the company millions.
Mining Medical Journal Articles Yields New Treatment and Drug Development
Biotechnology and related industries spend more than $1 trillion on biomedical research in the U.S. annually, and much of that information is published as scholarly articles in publications like the New England Journal of Medicine.
Biogen Idec, a biotech firm based in Cambridge, MA, uses text analytics software to mine text-based medical literature for information that will help its scientists and researchers develop new drug treatments for diseases like lymphoma and rheumatoid arthritis. And with each new drug therapy costing on average $125 million and taking two to four years to develop, every bit of relevant information Biogen Idec finds on chemical compounds and other substances is valuable.
In some cases, information derived from text analytics, like unexpected side effects that another researcher may have discovered and published in a medical journal, leads the company to abandon potential drug therapies, saving millions of dollars that can be allocated to more promising drugs. There would be no way to tap the vast amount of medical literature for this type of valuable information without text analytics software. Manually trolling the articles simply isn’t cost effective or scalable.
Your Text Analytics Story
There are many well-documented stories about companies successfully using text analytics to uncover potential new opportunities or save millions of dollars. I’d like to hear about your experiences.
Have you deployed text data processing capabilities in your EIM framework?
What success have you had thus far incorporating text analytics in your organization?