natasha's corner

I’ve been pretty excited about the possibilities presented by OpenAmplify – I wrote a bit about it in my previous post. So I got thinking… Twitter is a good obvious place to start with text analysis, but wouldn’t it be cool to see the top topics and sentiment for any website you’re looking at?

For example, say I’m thinking about buying a Kindle. I can go to Amazon.com and read through the 5000+ reviews. But what if I just want a summary? Amazon provides ratings, but that doesn’t tell me what I really want to know. In particular, what are the key things people are talking about? And how do they feel about them? Sure, I could copy/paste the URL into some tool and get the analysis, but that’s way too much work and I’ll probably forget about the tool when I need it anyway.

This is where Ubiquity comes in. Ubiquity is an add-on for Firefox that gives you the power to do more within your browser. For instance, you can select an address and immediately see a map. You can quickly shorten the URL you’re looking at so you can post it to Twitter. You can even tweet directly within the context of what you are reading. The beauty of Ubiquity is that it doesn’t interrupt your workflow to accomplish related tasks. You can read more about it here: http://labs.mozilla.com/ubiquity.

It’s easy to see that Ubiquity provides the perfect platform to incorporate the kind of analysis provided by OpenAmplify. It can expose the hidden information in a website that you otherwise could spend hours hunting down. This is where my Ubiquity command, “amplify”, comes in.

Here is how it works:

1. Go to any website, like the Kindle reviews page on Amazon.com.

   
   Kindle reviews on Amazon.com

2. Activate Ubiquity (Alt+Space) and execute the “amplify” command.

   
   Results of the “amplify” Ubiquity command

That’s it. You don’t need to open a new window, launch an external tool, or do any keyword searching. You get the sentiment analysis right in context, and that can reveal interesting insights.

So, how do you get this set up on your computer? It’s easy:

1. Install Firefox.
2. Install the Ubiquity add-on for Firefox.
3. Subscribe to my “amplify” command feed.

Here are some ideas (besides my Kindle example above) to try out once you have the command installed:

• Amplify CNN.com and compare it to FoxNews.com.
• Open up an e-mail in Gmail, select the text, and Amplify it.
• Go to your favorite blog and Amplify it.

Any other ideas for this type of sentiment analysis? Please share in the comments.

I recently learned about OpenAmplify, a web service that uses Natural Language Processing (NLP) to extract meaning from text. I’m very familiar with NLP because I’ve worked on the Text Analysis team at SAP (previously with Inxight Software), so I was very interested to see OpenAmplify provide this capability for free and online. It’s the first such service that I’ve heard of and I wanted to try it out.

So, I put together a little demo using Twitter and Xcelsius, the product I’m currently working on. Here’s how it works:

1. Twitter supplies the data.
2. OpenAmplify analyzes it for semantic content.
3. Xcelsius displays the data.

Try it out for yourself. (Note: Only single-word keywords will work right now.)

Those who are geekily-inclined can continue reading for the “how.” The rest of you can stop reading now.

Getting this set up was actually really easy and quick. Both Twitter’s and OpenAmplify’s APIs are easy to use and easy to connect. Here is what an OpenAmplify API call looks like when using Twitter as the data source:

http://portaltnx.openamplify.com/AmplifyWeb/AmplifyThis?apiKey=[your API key]&sourceURL=http://search.twitter.com/search.atom?q=[keyword]

To get this into Xcelsius, you first need to create an XML map to that URL in your Excel spreadsheet. Then, you set up the XML Map connection and with a little concatenation, link the URL to a cell that inserts the keyword at the end. (Feel free to e-mail me if you have questions about how to get this working.)

That’s all there is to it. Seriously.

In terms of functionality, I think OpenAmplify is rather limited. In their “About” page, they claim that OpenAmplify “identifies the significant topics, brands, people, perspectives, emotions, actions and timescales.” While that’s probably true, it would be nice to see the data by type (e.g., who are the people? what are the perspectives? what are the emotions?). As it is, you just get a list of “topics” and “actions” with ratings for polarity (positive, negative, or neutral). It would also be nice to get the supporting evidence that shows why each topic got the rating it got as a list of all the positive statements and all the negative statements. The style analysis (”slang” and “flamboyance”) might be fun, but I have a hard time imagining real uses for it. The demographics data, on the other hand, is very useful and I’m glad the OpenAmplify team says they will focus more on this in the future.

The latest release of OpenAmplify seems to have some good improvements in it, including performance improvements and the addition of “intentions” (what are people doing or intend to to). Just note that if you want to use the latest release, you actually have to use a different base URL for your API call:

http://portaltnx.openamplify.com/AmplifyWeb_V11/

rather than

http://portaltnx.openamplify.com/AmplifyWeb/

[A note for any OpenAmplify folks who may be reading this: You might want to update your documentation to point to the latest release URL. Not everyone reads your blog.]

I did not use this latest release because I wasn’t aware of the difference in URLs, but I’ll try to upgrade to it in the future and see how it works.

Overall, I am impressed with OpenAmplify for two reasons. One, it provides a valuable service for free, and two, it uses a community model. Rather than building applications themselves, the OpenAmplify team provides the tools for other people to do it. This can be very powerful, as demonstrated by Apple’s App Store, and I hope it takes off for natural language processing as well. Twitter seems to be a popular choice for analysis at the moment, but I’m really interested to see what other applications people find for OpenAmplify and NLP. I think there is a lot of potential here.

UPDATE: This little app was blogged by OpenAmplify!

The new Wolfram|Alpha “computational knowledge engine” is the coolest thing I’ve seen in a long while. My first impression was that this was just a big fancy calculator to help people solve NP-complete problems and complex differential equations and whatnot. Not that this wouldn’t be impressive in its own right, but it’s not exactly something I would use (though I could have used it back in college, when I was smart). The really cool thing about Worlfram|Alpha, though, is that it has a myriad of possible uses.

Read more on Opinion Road »

They spelled out "ten" and "seventeen," but I guess they just couldn’t
squeeze in 3 more letters for the proper spelling of "through."

I’ve always had a problem saying “he” or “she” when I really want to say “they.” For example, “The user can read the help information before they decide on the best option” just sounds so much better than “The user can read the help information before she decides on the best option.” The user, in this case, is gender-neutral so why do I have to choose a gender when talking about them? The other option, of course, is “he/she,” but that becomes even more awkward.

I’m happy to see that Tufte agrees with me:

Do not use masculine pronouns—use plurals
Even though it may not always be grammatically correct, you should say “they” instead of “him or her”
and it will sound better—both because it’s shorter and because no one can be alienated. Why risk not communicating simply because someone may be sensitive?

– Edward R. Tufte’s Presentation Tips

The moment one definitely commits oneself, then Providence moves as well. All sorts of things occur to help one that would never otherwise have occurred. A stream of events issues from the decision, raising in one’s favor all manner of unforeseen accidents, meetings and material assistance that no one could have dreamed would come their way. Whatever you can do or dream you can do, begin it. Boldness has genius, power and magic in it. Begin it now.

– Goethe

I didn’t see it then, but it turned out that getting fired from Apple was the best thing that could have ever happened to me. The heaviness of being successful was replaced by the lightness of being a beginner again, less sure about everything. It freed me to enter one of the most creative periods of my life.

– Steve Jobs

Take the time and money and effort you’d put into an expensive logo and put them into creating a product and experience and story that people remember instead.

– Seth Godin

In 1060, an imperial decree barred “every woman, every child, eunuch, smooth faced person, and female animal” from Athos, which suggests that there had been incidents of inventive nonchastity over the years.

– Frommer’s guide for Greece