Analytics for Human Information: Optimize Information Categorization with HP IDOL

Conceptual search has the amazing ability of providing insight into information that may not, at face value, seem to hold anything special. People often talk about how with conceptual search you can discover things in your data that you didn’t even know to look for in the first place. It’s an exciting, game-changing prospect, no doubt, but for now I want to talk about the less sexy, but equally valuable elements, to any insight exercise—categorization.

 

The very powerful—but less sexy part of—conceptual search

 

One of the most important capabilities of HP IDOL is its ability to take categorization to the next level. Let’s say you are a mutual fund company and you want to determine what kind of information is contained in your inbound emails. To accomplish this kind of task, you could take one of several paths:

 

  1. You could have your customer service folks read each email, and then apply a categorization ID or tag to the email, which you could later search—assuming you have a list of all the tags handy.
  2. You could have a machine read the email, and based on the satisfaction of your manually created keyword searches (regardless of how complex) and other manual approaches, you could apply a category ID to each email.
  3. You could let IDOL automate the process.

As you can probably tell, options one and two are major time killers, laden with lots of manual processing. They can not only take forever, but can then leave you with varying degrees of accuracy. Nothing against us humans, but to err is human, and especially in an organization with thousands of emails coming in, this type of task would not only be tedious, but likely quite error-prone. In situations like this, turning to technology that specializes in understanding and categorizing information is the way to go. Enter HP ExploreCloud, a Saas-based offering that provides insight and analytics across multichannel interactions.

 

Powered by HP IDOL, ExploreCloud helps you uncover insights across all channels: web, mobile, social media, email, contact center, database, and storefront, so that you can organize and quantify content in a consistent, objective manner, resulting in data that is more accessible and consistent. And you can maintain existing legacy taxonomies and/or enrich them with contextual understanding. When you go beyond the limitations of what keywords can help you do, your whole world opens up. You can also discover the "unknown unknowns,” or topics you did not know to look for in the first place.

 

ECM_v04_309x304.png

 

For those of you who are familiar with IDOL, you know that it fully supports keyword search to enable categorization. We aren’t doing away with this philosophy—we just recognize its limitations and go beyond what keyword search offers. Since keyword and Boolean methodologies rely strictly on query terms, without taking into consideration the context of the terms, keyword search includes many false hits when categorizing information and it can exclude relevant documents that do not contain specific query terms. That leaves out quite a bit of information that could very well be relevant and leaves you with data blind spots.

 

A little story about contextual search  

 

When a computer can understand that the letters “D-O-G” mean a dog, man’s best friend, a Labrador, or an animal that likes to go for walks, the process becomes more human and the computer can do more of the work for us. Yet the lack of structure in human information still makes the search process challenging for the simple reason that people search or analyze data using an attribute of the data, such as the date a recording was captured, the people pictured in a photo, or whether a website gives a positive review of a product. This requires some form of metadata to be tagged to the item, or generated on the fly, as the item is saved. If no such metadata exists, you will have difficulty finding it, or you may not be able to find it at all. This issue is not an easy one to solve without human involvement.

 

For example, how can software tell if a picture is of a yellow rose, a yellow Labrador named Rose, or a girl named Rose in a yellow dress? Compounding these challenges, human information is often more difficult to manage than structured or semi-structured information in terms of size, organization, and availability.

 

To wrap up, you can see how using our technology is going to get those emails or tweets categorized way faster than tagging and bagging them one by one, or even in sets, using only keywords. IDOL can save you a lot of time, reduce the cost of many different types of business information activities, and get you a lot closer to perfection than any human could think possible.

 

#HPAHIB

 

Edited by Robin Hardy

Comments
it supp0rt(anon) | ‎12-25-2013 12:55 PM

IDOL is indeed a very useful tool when it comes to organizing and categorizing emails that can take most of your time.  This tool can help you maximize your time and effort as well as your budget.

Leave a Comment

We encourage you to share your comments on this post. Comments are moderated and will be reviewed
and posted as promptly as possible during regular business hours

To ensure your comment is published, be sure to follow the Community Guidelines.

Be sure to enter a unique name. You can't reuse a name that's already in use.
Be sure to enter a unique email address. You can't reuse an email address that's already in use.
Type the characters you see in the picture above.Type the words you hear.
Search
Showing results for 
Search instead for 
Do you mean 
About the Author
Dan Burke serves as a vice president of HP Software. He is in SME within Power and Emerging technologies, focused on HP Autonomy Explore and...


Follow Us
The opinions expressed above are the personal opinions of the authors, not of HP. By using this site, you accept the Terms of Use and Rules of Participation