IBM Business Analytics Goes to the Oscars

University of Southern California Annenberg Innovation Lab, IBM, and the Los Angeles Times are measuring social media sentiment related to the upcoming 84th Academy Awards

Petaling Jaya, 22 February 2012 - Social media users are weighing in with their Oscar® picks and pans, according to the University of Southern California Annenberg Innovation Lab, IBM (NYSE: IBM) , and the Los Angeles Times who are measuring social media sentiment related to the 84th Academy Awards. The project, dubbed a ‘Senti Meter’, relies on new sophisticated analytics and natural language recognition technologies to gauge positive and negative opinions shared in millions of public tweets.

Focused on the Best Actor, Best Actress and Best Picture categories, the goal is to establish a model for measuring the volume and tone of worldwide Twitter sentiment to better understand moviegoers' opinions. The results are intended to illuminate how advances in technology can help identify important consumer trends. In this case, movie studios would be able to better understand their audience preferences and use social media to improve their marketing programs and in turn improve box office results.

The Times has published information about the project including an infographic illustrating ongoing sentiment. The analysis will be updated at www.latimes.com/senti-meter as sentiment evolves over the weeks leading up to the Academy Awards on February 26, 2012.

"This project is about identifying 'The People's Oscar,' which means moving beyond pundits' opinions of who the winners may be, to understanding who real moviegoers want to see receive the highest accolades of the industry," said Professor Jonathan Taplin, Director of the USC Annenberg Innovation Lab. "We want to illustrate how new technologies can capture valuable information and opinions derived from the voices of influential movie fans."

The work between the USC Annenberg Innovation Lab and IBM is part of an ongoing collaboration to explore how technology can be used by organizations from news outlets and journalists, to movie studios and retailers, in order to better understand, respond, and predict public sentiment.

"The ability to apply a quantified measurement to social media chatter surrounding the top films and performances of the season, and to do so over a period of time, adds a valuable new dimension to The Times awards coverage," said Times Assistant Managing Editor Arts and Entertainment, Sallie Hofmeister. "We're very interested in developing and embracing new technologies to inform our reporting and working with IBM and USC has made this early stage social sentiment tool possible."

In the case of the Oscar race, innovative analytics and language software from IBM is being used that distinguishes nuance and sarcasm in order to pinpoint relevant opinions of the nominated films, actors and actresses and show noteworthy trends. To date, USC Annenberg and IBM have also applied similar techniques to film forecasting, sports and fashion retailing in an effort to identify social media trends and better understand public opinions.

In fashion retailing, IBM recently projected an eight percent surge in men’s apparel sales for the first quarter of 2012 retail sales in U.S. stores.

“The forecast of men’s apparel sales reflects a growing trend: men are definitely developing a taste for fashion – especially in business attire,” said Jill Puleri, global retail leader for IBM Global Business Services. “They’re tired of the khaki pants and golf shirt uniform that ruled many offices for the past couple decades. They’re looking to dress more stylishly – choosing items like skinny ties and suspenders that present a more polished look.”

Demonstrated to be accurate to 97.26 percent (the average across the multiple retail categories listed above), the IBM forecast relies on 22 years of historical data and sophisticated analytics software developed by IBM to evaluate both long-term trends and seasonal peaks. IBM consultants use these predictive techniques to help clients improve performance by addressing complex issues of supply and demand. These techniques also aid clients in planning product mix and new store locations.

In producing the forecast, IBM uses economic data gathered by the U.S. Census Bureau. The data is derived from a survey of retail store establishments. These store establishments are a representative sample and are not inclusive of all industry activity in this category.

For more information about: The University of Southern California Annenberg Innovation Lab visit www.annenberg.usc.edu; IBM and analytics, visit www.ibm.com/analytics; or Los Angeles Times, visit www.latimes.com/aboutus.

For more information, visit www.ibm.com/gbs/bao.