About half of the respondents said they get movie recommendations from friends and family, and 16% mention co-workers as their movie review go-to sources. According to the research, face-to-face recommendations overshadow recommendations through social media: Facebook offers up 11% of the movie recommendations that responds said they rely on, and Twitter only accounted for 1% of movie recommendations that influence those polled. Continue reading
Two researchers at HP Labs, Sitaram Asur and Bernardo Huberman, have discovered that you can accurately use Twitter mentions to predict how well a movie will perform in its first release weekend. Asur and Huberman monitored movie mentions in 2.9 million tweets from 1.2 million users over three months for 24 movies.
They then built a computer model, which looked at two variables: the rate of tweets around the release date, and the number of theaters its released in. Lo and behold, their model was 97.3% accurate in predicting opening weekend box office. By contrast, the Hollywood Stock Exchange, which has been the gold standard for opening box-office predictions, had a 96.5% accuracy.