"A recent study [pdf] by Sitaram Asur and Bernardo A. Huberman at HP Labs found that it's possible to use Twitter chatter to predict first-weekend box office revenues simply based on volume of tweets. The predictions were even more accurate when they introduced sentiment analysis (i.e. classified tweets as positive or negative)."
This is exactly the type of stuff that I did for a summer internship at a marketing research company in town. I sat in front of a computer 40 hours a week, and did "sentiment analysis (i.e. classified tweets as positive or negative)." Most of what I did was grade blogs and comments and newspaper articles about an insurance company that was involved in the hurricane Katrina disaster. It was so boring I would sometimes break down in tears at the end of the day.
No comments:
Post a Comment