---

E-mail | Print | Comments | Request Reprints | E-Mail Newsletters | My Yahoo! | RSS

By This Author Leah Hoffmann • First Job: Steven Pinker • First Job: Todd Hanson • Can A Computer Read You Like A Book? More Headlines Related Quotes AMZN 26.72 - 0.06 GOOG 381.37 + 3.42 IBM 75.88 + 0.66 MSFT 24.36 + 0.14 Most Popular Stories Forbes Takes Bono As Partner Post-Castro Capitalism? MySpace Gets Googled Making Money In A Virtual World Most Satisfying Cars 2006

Ever searched Google for advice on vacation destinations? Unless you're traveling to an obscure village in Siberia, chances are your search turned up thousands of relevant Web sites. Looking at all of them would be tedious and time consuming. But what if there were a way to sort them based on whether or not they're favorable?

As it turns out, there is. "Sentiment analysis," as the field of research is known, is a hot topic among computer scientists these days. The goal is to create computer programs that can determine whether a document is positive or negative. And corporations, like IBM (nyse: IBM - news - people ), Microsoft (nasdaq: MSFT - news - people ), Google (nasdaq: GOOG - news - people ), and Amazon.com (nasdaq: AMZN - news - people ), are paying attention to the results. Successful applications could help automate market and product research and dramatically alter the future of a simple Internet search.

The most common approaches begin by identifying certain "indicator words" within a text--words like "good," "bad" or "beautiful"--that convey positive or negative emotions. But that's not as easy as it sounds.

"The variety of words that people use for subjective expressions is staggering," says Janyce Wiebe, a professor of computer science at the University of Pittsburgh. Wiebe and her colleagues have already assembled a dictionary of some 8,000 indicator words and phrases.

"The dictionary tells you whether a word is positive or negative when it's taken out of context," Wiebe explains. "The challenge is to figure out whether it's positive or negative in each individual instance."

There are a number of different ways to accomplish this. Wiebe uses a program that can--with assistance from humans who "train" it to recognize the right answers--learn how context impacts the meanings of words.

Peter Turney, a researcher at the Canadian National Research Center's Institute for Information Technology, uses his own dictionary of indicator words to assign each of a document's adjectives a positive or negative value. He then averages these values to create an overall opinion score. Accuracy rates for these methods range from 70% to 85%, depending on the kind of document.

If you're trying to classify documents within a specific field--reviews for a particular product, for instance--you can increase accuracy by customizing your indicator words. (After all, a "hot" refrigerator is bad, but a "hot" nightclub is not.) That's the approach taken by Norwegian search company Fast Search and Transfer ASA, which unveiled a customizable sentiment analysis program, Marketrac, last year. FAST has already licensed Marketrac to more than a dozen clients, who use it to keep track of everything from online hotel reviews to the speeches of European business leaders. Licensing fees for the program are more than $100,000 per year.

Other potential applications in the field of sentiment analysis include automated flame detectors for online bulletin boards, tracking systems for stock market reports and programs that monitor movie or product reviews. You may also one day be able to do a simple Web search to find out what people are saying about a given issue.

"When people begin expressing their emotions, their language gets very florid and very complicated, very quickly," says Lillian Lee, a computer science professor at Cornell University. It will be a few years before scientists are able to refine their algorithms and get greater accuracy with a range of documents. Once they do, however, it's a safe bet that companies will be giving them a thumbs up.

Want to track news by this author or about this industry? Forbes Attache makes it easy. Click here.

Article Controls

E-mail | Print | Comments | Request Reprints | E-Mail Newsletters | My Yahoo! | RSS

A Pause In The Action
Albert Bozzo
The Fed won't lift interest rates this time, but it probably should.

• Market Outlook: No Fear Of The Fed
• Commentary: The Short, Sharp Shock
• Notes On The News: Will The Fed Follow Europe?

Forbes Takes A Partner

Post-Castro Capitalism?

Most Satisfying Cars

Longing For Short ETFs

E-Mail Alerts Companies   Amazon.com   Microsoft   IBM   GOOG Topics   Software   E-Commerce   Internet   Research And Development Enter E-Mail Address: FAQ  Privacy Policy Free Trial Issue Gift Subscriptions

Brought to you by the sponsors below

The World's Largest Luxury Showroom. Find the right luxury vehicle at the best price and buy your new car with confidence on ForbesAutos.com. ForbesAutos.com featured vehicle: Jaguar XJ Super V8 The Super V8 with its 400-horsepower supercharged V8 engine wants for nothing. You can get a free price quote from a local dealer or build your own Jaguar XJ Super V8

Marketplace (Sponsored Links)

Find Real Estate

more >

Investment Opportunities provided by
Enter City & State or Zip	Pre-Foreclosure Foreclosure (Auction) Bank Owned (REO) Resale New Home For Sale By Owner
Learn More: Foreclosures On the Rise Nationwide... Locating Lucrative Investment Properties...

Book Review Kathleen Archambeau Book Review Glass Ceilings Tom Van Riper Why do women still hit barriers to top management jobs in the corporate world? Search Books Title Author Item Number All Fields        Advanced Search     New & Notable

Credit Reporting & Monitoring: Discover how it can protect your credit well-being. First Name Last Name

Blank Slate What if you could pick one thing and start over from scratch? What would you change?