Crunching feelings not numbers
Today’s NY Times has an interesting article about sentiment analysis, a burgeoning field where, researchers try to figure out how people on the web feel about certain topics or businesses.
The article points out how the people behind these research firms are trying to deal with linguistic grey areas caused by slang, irony, and sarcasm. But what’s even more interesting is their trying to measure the actual “heat” of the sentiment being expressed (it seems everyone on the web either loves or hates something, there is not much apathy or middle-ground).
To get at the true intent of a statement, Ms. Pang developed software that looks at several different filters, including polarity (is the statement positive or negative?), intensity (what is the degree of emotion being expressed?) and subjectivity (how partial or impartial is the source?).
For example, a preponderance of adjectives often signals a high degree of subjectivity, while noun- and verb-heavy statements tend toward a more neutral point of view.
It’s a field to keep an eye on, and it will be even more interesting when we start seeing businesses making changes based on consumers actual, expressed feelings on the web.
