"The rise of blogs and social networks has fueled a bull market in personal opinion: reviews, ratings, recommendations and other forms of online expression," writes Alex Wright in a recent New York Times article. "For computer scientists, this fast-growing mountain of data is opening a tantalizing window onto the collective consciousness of Internet users."

The emerging field of sentiment analysis, he reports, enables companies to make better sense of the chatter. Wright offers the following real-world examples:

• After stadium officials erroneously told fans that a baseball game had been canceled—it was only a rain delay—ticket marketplace StubHub denied their requests for refunds because the game had been played. With the assistance of a monitoring device from Scout Labs, however, the company noticed a worrisome spike in negative online comments. The real-time insight enabled StubHub to change course, offering unhappy customers credits and discounts: it also prompted a review of the general bad-weather policy.
• With the Newssift tool—an experimental program from the Financial Times—users will discover positive sentiment for Wal-Mart dominates negative sentiment by a ratio of 2:1. Throw in the term Labor Force and Unions, however, and the ratio plunges to a less desirable 1:1. "Such tools," he notes, "could help companies pinpoint the effect of specific issues on customer perceptions, helping them respond with appropriate marketing and public relations strategies."

The Po!nt: "As sentiment analysis algorithms grow more sophisticated, they should begin to yield more accurate results that may eventually point the way to more sophisticated filtering mechanisms," says Wright. "They could become a part of everyday Web use."

Source: New York Times. Click here for the full article.

Upgrade Your MarketingProfs Membership: Become a Pro Member and gain instant access to hundreds of exclusive, cutting-edge articles, case studies, templates, tools, online seminars, research and how-to guides to make your marketing smarter and more effective.

→ end article preview
Read the Full Article