Skip to Content
Uncategorized

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.

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?

Keep Reading

Most Popular

Workers disinfect the street outside Shijiazhuang Railway Station
Workers disinfect the street outside Shijiazhuang Railway Station

Why China is still obsessed with disinfecting everything

Most public health bodies dealing with covid have long since moved on from the idea of surface transmission. China’s didn’t—and that helps it control the narrative about the disease’s origins and danger.

individual aging affects covid outcomes concept
individual aging affects covid outcomes concept

Anti-aging drugs are being tested as a way to treat covid

Drugs that rejuvenate our immune systems and make us biologically younger could help protect us from the disease’s worst effects.

Europe's AI Act concept
Europe's AI Act concept

A quick guide to the most important AI law you’ve never heard of

The European Union is planning new legislation aimed at curbing the worst harms associated with artificial intelligence.

Stay connected

Illustration by Rose WongIllustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.