Study of Movie Audiences: IBM and USC Analyze Emotions Behind Tweets
By Karla Robinson
November 30, 2012
November 30, 2012
- In the 11 days leading up to Thanksgiving and through the weekend, “Twilight: Breaking Dawn – Part 2” generated millions of tweets, but unlike many of the other movies playing over the holiday, a fair share of the social chatter was negative.
- A deeper analysis of the tweets found that the disappointment had more to do with the series ending, showing how engagement measurements have become more accurate.
- IBM researchers partnered with the USC Annenberg Innovation Lab to analyze more than 5 million move-related tweets, finding “Twilight” accounted for 4.25 million. “Skyfall” came in second with only 700,000. However, the Bond film’s social sentiment was 90 percent positive, while “Twilight” dropped from 90 to 75 percent by Saturday.
- “The mystery why a hit film like ‘Twilight’ might generate such a reception on Twitter could foreshadow the next advance in computer science,” notes The Hollywood Reporter. IBM used the artificial intelligence computer Watson, famous for beating humans on “Jeopardy!,” to determine the emotional content of tweets.
- Steve Canepa, general manager for IBM’s Media & Entertainment Group, explains that “studios once had the luxury of slowly releasing a film, building audience momentum over time and adjusting marketing campaigns based on what was or wasn’t working,” THR reports.
- “But now that social media audiences are rendering their snap viral judgments, Canepa believes it’s more important than ever that studios adapt likewise by getting their marketing correct at a film’s launch. And that means understanding more quickly than ever how audiences are reacting.”
- “Canepa adds that predictive analytics driven by social sentiment also might help researchers appreciate which film and TV storylines work best in particular genres to precise demographics. Or which Hollywood stars match up best with each other,” the article explains.
No Comments Yet
You can be the first to comment!
Leave a comment
You must be logged in to post a comment.