Twitter Not So Good At Predicting Box Office Revenues After All
A new study of tweets about movies suggests they are not necessarily a good predictor of box office revenues, say computer scientists
The online social network Twitter has recently gained a reputation for a certain degree of clairvoyance.
The combined wisdom of the Twitter crowd can predict, among other things, the movement of stock markets, the spread of news and the box office revenues of movies. Or so we’re told.
Today, Felix Ming Fai Wong and pals at Princeton University in New Jersey, pour cold water on the idea that Twitter is a reliable predictor of the future, at least as far as the success of movies is concerned.
This story is only available to subscribers.
Don’t settle for half the story.
Get paywall-free access to technology news for the here and now.
Subscribe now
Already a subscriber?
Sign in
You’ve read all your free stories.
MIT Technology Review provides an
intelligent and independent filter for the
flood of information about technology.
Subscribe now
Already a subscriber?
Sign in
During this year’s Oscar season (2 February to 12 March), these guys collected 1.7 million tweets that contained the titles of 34 recently released or Oscar-nominated films. Of these, about half turned out to be irrelevant. (For example, “thanks for the help” does not refer to the movie The Help!)
They then classified the remainder according to whether they contained positive or negative comments and whether they were tweeted before or after the person had seen the movie, to distinguish between hype and genuine opinion.
Finally, they collected reviews from the Internet Movie Database and RottenTomatoes.com about the same films
Wong and co then crunched this data to see how reviews on Twitter compare to those from the other online sources.
It turns out that a number of interesting patterns emerge. For example, Twitter users post far more positive reviews than negative ones, which Wong and co say may have implications for marketers.
“Instead of focusing on reducing the negative reviews from a few dissatisfied customers, it may be better to focus on enhancing the already high proportion of positive reviews on online social networks and use virality effects to influence consumers,” they say.
They also found that Twitter’s predictive ability is limited. For example, the reviews on Twitter do not necessarily reflect the reviews that appear on other online sites.
What’s more, in contrast ot other studies, the Twitter data does not always translate into box office revenue (although in some cases it can). “Marketers need to be careful about drawing conclusions regarding the net box-office outcome for a movie,” conclude Wong and co.
So by this reading, Twitter’s predictive ability seems to have been overhyped, at least as far as box office revenues are concerned. It’ll be interesting to see whether a similar story emerges for other areas such as stockmarkets.
Ref: arxiv.org/abs/1203.4642: Why Watching Movie Tweets Won’t Tell the Whole Story?
