Baseball is like church. Many attend but few understand. — Wes Westrum
I cannot tell a lie.
I’m extremely excited that my Texas Rangers made it to the World Series for the second year in a row.
Growing up in north Texas, the Rangers were a team we loved to hate... or is that hated to love? They had no pitching. They rarely had winning seasons. But they were our team.
IBM and USC Annenberg have partnered to use analytics technology to catch Major League Baseball fan sentiment via the social media for this year's MLB World Series matchup between the St. Louis Cardinals and Texas Rangers beginning tonight in St. Louis, Missouri.
And they still are. Tonight, in Saint Louis, they’ll be playing the Cardinals in the first game of this year’s World Series.
Which is why it’s also exciting to note that today, IBM and the University of South California Annenberg Innovation Lab announced a new social media analysis project focused on Major League Baseball during the World Series.
The USC Annenberg Social Sentiment Index is being compiled by students and relies on IBM Social Analytics technology to analyze millions of Tweets in order to assess public social media engagement and opinion from sports and film to retail and fashion.
Students from USC have done an initial analysis of the National League Championship Series (NLCS) and will now broaden the index to follow the World Series games beginning today to determine “social media MVPs.”
The goal is to uncover hidden insights from Twitter followers that could help better understand player and team sentiment, and illustrate how advanced analytics technologies can help identify important trends.
The students have used the technology for an initial test of more than 1.5 million public baseball-related tweets during the National League Championship Series, gauging positive and negative nuances and establishing overall sentiment rankings among a sampling of NLCS players.
Initial index findings show:
- The Cardinals’ Chris Carpenter garnered the highest number of tweets indicating sentiment at 1,573 -- 61.4 percent positive and 21.6 percent negative.
- However, fellow Cardinal David Freese, a fan favorite and official NLCS MVP of the pennant race, garnered 768 tweets (89.3 percent of his tweets were positive and only 15.4 percent negative), securing one of the highest T scores -- winner of the most uniformly positive tweets.
- The Texas Rangers are winning the Twitter buzz battle: the American League’s social media champion was the focus of more than 56,600 tweets -- five times more than the St. Louis Cardinals -- with 79 percent of the tweets being positive. While the Cardinals are behind in the number of postings, they have matched the Rangers’ level of enthusiasm in their tweets. St. Louis garnered 11,500 tweets, 80 percent of which were upbeat.
For baseball fans everywhere, social media is now as integral a part of the game experience as keeping score or enjoying hot dogs and peanuts.
In fact, during the post season, a banner behind home plate has been encouraging spectators to connect using the hashtag #postseason, giving fans an opportunity to both share and learn from others instantly, and providing researchers with an unfiltered voice of the fan that is ripe for analysis.
USC and IBM are collaborating to broaden student skills in analytics and demonstrate how Watson-inspired technologies, such as sophisticated semantic and linguistic analysis software, can provide new insights into public opinion by crunching complex data in real-time.
Analyzing data is not a game
“Analyzing data is not a game -- it’s an important way to understand different constituencies and gain competitive advantage,” said Rod Smith, Vice President of Emerging Technology, IBM. “Whether it’s analyzing fan sentiment during a sports event, hospital patient data for personalized treatment programs, or the latest fashion trends for more targeted marketing campaigns, organizations are realizing the value of analytics to better respond to customer needs.”
The ability to glean insights into viewpoints from Big Data -- structured and unstructured information -- carries value across all aspects of baseball, from the media outlets covering reactions to the game and players, to businesses marketing to the fans, and most importantly, to the players and coaches themselves.
In fact, analyzing data to generate actionable insights in the baseball world has already afforded major league teams better decision-making to create productive ball clubs year after year. For example, Oakland Athletics general manager Billy Beane has become famous for his [explain what he did for people like me that don't know] through the use of analytics, made famous by Moneyball: The Art of Winning An Unfair Game, the best-selling book and motion picture.
IBM’s collaboration with the USC Annenberg Innovation Lab is part of its continued efforts to advance student skills in analytics across academia. IBM is working with more than 6,000 universities around the world to develop curricula and provide training, resources and support for business analytics.
The USC Annenberg Social Sentiment Index on baseball is being conducted as part of the 2011 IBM Information on Demand and Business Analytics Forum taking place next week in Las Vegas, October 23 to 27. (Blogger’s note: I’ll be in attendance blogging the general sessions, and Scott Laningham and I will be LiveStreaming from the IOD Expo floor.)
The index on baseball will be updated during the World Series on asmarterplanet.com to illustrate the ongoing shifts in fan sentiment throughout the series.
For more information about IBM and analytics, visit www.ibm.com/analytics.