Journey through Enterprise IT Services
In Journey through Enterprise IT Services, Nadhan, HP Distinguished Technologist, explores the IT Services industry, and discusses technology trends in simplified terms.

Sentiment analysis should not be a one-time activity

So, here I am watching with great interest, two candidates furiously debating weeks before the upcoming election for public office.  The channel I am watching has a real-time feed at the bottom of the TV screen that represents the feelings of the male and female "undecided" voters on a position taken by either candidate.  You can see the colored lines for men and women going in waves at various points in the debate with the sentiments changing in real time.  However, these sentiments are captured only for a particular period of time.  When the debate is over, the sentiment is no longer visible.  I wish we had the ability to capture the sentiments on a sustained basis at any point in time across a wide geography.  I am sure the candidates would like this too!

 

By analyzing the structures and meaning of language, HP’s Autonomy Intelligent Data Operating Layer (IDOL) determines the positive and negative characteristics of each piece of information and creates relevant classification systems. IDOL can determine the degree to which a sentiment is positive, negative or neutral for the entire content or a segment of the content.

 

Most likely, the TV channel did not have Autonomy IDOL but had a room full of viewers equipped with a device that can be controlled to readily communicate one’s reactions. (Just like your favorite “IDOL” show where you get to vote on a contestant’s performance.) 

 

After the debate, I go to the social media and see a flurry of messages.  As a human being, I filter out the essence of what is being expressed by my fellow constituents.  However, this takes time and effort on my part.  I shut down my BYOD device for the day and wish there were tools that could do this for me while I go to my daughter’s ice-cream social.  I have had enough of configuring my mind to think like a computer; forcing my mind to cast everything in rows and columns of relational data.  Life, after all, is not a relational database. 

 

So, it was with great interest that I read about how HP Autonomy suite of tools can do what humans have been doing since the dawn of time.  We are now at a point where computers (software) are thinking like humans instead of like machines.

 

HP's Autonomy IDOL technology uses sophisticated pattern-matching techniques and probabilistic modeling to interpret information in much the same way humans do.

 

It is quite possible you have voted on one of those <pick your favorite> IDOL shows.  But, when it comes to tools that can effectively analyze the sentiment on a sustained basis, my vote would be for Autonomy IDOL.

 

How about you?  What steps do you take to understand the sentiment of a select group of users?  What tools do you have in place?  Have you contributed to the underlying sentiment on a topic of interest recently?  Please let me know. 

 

Or express your sentiment by following me on Twitter.  I will catch up on it later – because, you see, I have to go for my daughter’s ice-cream social and address her sentiments.

 

Connect with Nadhan on: Twitter, Facebook, Linkedin and Journey Blog.

Comments
Seth Grimes(anon) | ‎10-26-2012 12:05 PM

Nadhan, if you're by chance in the Bay Area, you should check out my conference next week, the Sentiment Analysis Symposium. In any case, it's particularly important to learn about analyses that go beyond the positive/negative/neutral classifications, at entire-content or segment level, that you right about, to resolve opinions, mood, and emotions at a feature level. Autonomy IDOL, of course, has rich feature-extraction capabilities, but I do wonder when we're going to see deeper sentiment analysis from HP. I'd welcome knowing more!

Nadhan | ‎10-26-2012 03:58 PM

Seth, Thank you for the reference to your conference.  Looks very interesting!  

 

In addition to the links I have provided in the post to Autonomy sites, the upcoming conference in Frankfurt will provide ample opportunities to "Discover" Autonomy features!   Hope to see you there !

 

Connect with Nadhan on: Twitter, Facebook, Linkedin and Journey Blog.

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
About the Author
About the Author(s)


Follow Us