Social Media Can Predict Country Music Hits-- Can It Predict Political Races As Well?

This morning a friend asked me if I was aware that Social Media could help radio programmers-- not to mention A&R executives and retailers-- determine which artists would make it big and which songs would be hits. Although they were talking specifically about the very formulaic and relatively simplistic country music genre, there's no reason why this report from Inside Radio couldn't be applied across the board to all genres of music.

Picking a hit record may still be an art, but there’s a lot more science at a programmer’s fingertips than ever before. And none is more reliable than social media chatter, according to preliminary research done by Stone Door Media Lab and MusicMetric.

Speaking at the Country Radio Seminar yesterday in Nashville, the companies said that after looking at four-weeks of correlations between 81 country records and 28 social and online metrics, a hit-predicting pattern developed. "A funny thing happened on our way to determining the role social and online media have on making country hits-- we discovered a predictive model," MusicMetric SVP Mark Tindle says.

Stone Door Media Lab’s Jeff Green says there’s still no foolproof method for determining probabilities for hits, but they have determined that data can identify a new single’s potential many weeks earlier. "These statistics prove that what many thought were hunches are really true," Green says.

The companies say they’re still working to develop the model but they believe it will one day be possible to pick a hit as little as four weeks before it debuts on the charts. MusicMetric of course sells analytics to the record industry and this new tool could be part of that product lineup.

If you can pick a country hit by studying social media traffic, there's no reason why you can't pick a Republican presidential nominee, right? And if this new approach goes beyond country, it may go into normal politics as well, and not just the formulaic GOP variety. In fact, last year we reported on a study by Joseph DiGrazia, Karissa McKelvey, Johan Bollen and Fabio Rojas at the University of Indiana illustrating how Twitter conversations can be used to predict election outcomes. Rojas, an associate professor of sociology at Indiana State, explained what they found in an OpEd, "How Twitter Can Help Predict An Election," for the Washington Post last August. "Digital democracy," he wrote, "is here. We no longer passively watch our leaders on television and register our opinions on Election Day. Modern politics happens when somebody comments on Twitter or links to a campaign through Facebook. In our hyper-networked world, anyone can say anything, and it can be read by millions."

I noticed the other day that best selling author and congressional candidate Marianne Williamson-- with over 800,000 social media followers-- not only has more social media clout than all her opponents combined, but that their combined followers are less than a daily rounding figure in her count. She's done something to make an impact on people's lives in a very meaningful way, well beyond partisan politics. As one Member of Congress mentioned to me when dismissing her main opponent, ex-Republican Wendy Greuel, "What has she ever done to help even one person outside of her immediate circle? She's a career politician but has she ever done anything to help anyone's life?" That's why Marianne has over 200,000 Twitter followers and Greuel, fresh off a widely-covered, albeit calamitous, city-wide election campaign against Mayor Eric Garcetti, has less than 7,000. Greuel is depending on endorsements from irrelevant career politicians like herself-- anti-working family hack Gavin Newsom is a perfect example-- and on laughable self-generated polls instead of any real enthusiasm.

This new world will undermine the polling industry. For nearly a century, conventional wisdom has argued that we can only truly know what the public thinks about an issue if we survey a random sample of adults. An entire industry is built on this view. Nearly every serious political campaign in the United States spends thousands, even millions, of dollars hiring campaign consultants who conduct these polls and interpret the results.

Digital democracy will put these campaign professionals out of work. New research in computer science, sociology and political science shows that data extracted from social media platforms yield accurate measurements of public opinion. It turns out that what people say on Twitter or Facebook is a very good indicator of how they will vote.

How good? In a paper to be presented Monday, co-authors Joseph DiGrazia, Karissa McKelvey, Johan Bollen and I show that Twitter discussions are an unusually good predictor of U.S. House elections. Using a massive archive of billions of randomly sampled tweets stored at Indiana University, we extracted 542,969 tweets that mention a Democratic or Republican candidate for Congress in 2010. For each congressional district, we computed the percentage of tweets that mentioned these candidates. We found a strong correlation between a candidate’s “tweet share” and the final two-party vote share, especially when we account for a district’s economic, racial and gender profile. In the 2010 data, our Twitter data predicted the winner in 404 out of 406 competitive races.

Why does this happen? We believe that Twitter and other social media reflect the underlying trend in a political race that goes beyond a district’s fundamental geographic and demographic composition. If people must talk about you, even in negative ways, it is a signal that a candidate is on the verge of victory. The attention given to winners creates a situation in which all publicity is good publicity.

This finding is remarkable because it doesn’t depend on exactly what people say or who says it. We measured only the total discussion and estimated each candidate’s share. It is this relative level of discussion that matters for tracking public opinion in electoral contests. Furthermore, social media data mimic what polls measure. For example, in Ohio’s 3rd Congressional District, we found that Republican Mike Turner got 65.4 percent of his district’s tweet share. In the final election, he got 68.1 percent of the two-party vote. The tweet prediction was off by 2.7 percentage points-- a figure that is within the margin of error of any poll.

This finding has profound implications for the democratic process. There are many nations that remain mired in poverty and do not have the infrastructure required for extensive polling. Furthermore, these nations often have governments that are suspicious of polling and try to suppress it. For these reasons, it is very hard to monitor elections. In contrast, as long as citizens have access to the Internet, they can talk about their views in a less-restricted manner. The “grassroots” buzz found in social media can be studied, and it will reveal how elections are conducted and if the state is respecting human rights. And as with U.S. elections, even if the people who use social media are not completely representative of the public, the amount of attention paid to an issue is an indicator of what is happening in society. Important events generate scrutiny that can be measured and studied.

Social media analysis is also important for elections in the United States. Polling favors the established candidates because it is relatively expensive. In contrast, social media analysis is cheap. Anyone with programming skills can write a program that will harvest tweets, sort them for content and analyze the results. This can be done with nothing more than a laptop computer.

The year before, Adweek's Charlie Warzel wrote that Twitter had embedded itself firmly into the fabric of 21st century communications in general-- and political communications specifically. "Twitter," he writes, "has become a veritable particle accelerator for news cycles and political battles... It is, for better or worse, the center of the political conversation, and it is transforming the way political campaigns and those who cover them do business."

“What happens on Twitter does not stay on Twitter-- it is not Las Vegas,” says Peter Greenberger, Twitter’s director of political ad sales in Washington, D.C. And if anyone in Washington has reason to smile these days, it’s him.

…[I]t took Twitter three years, two months and one day to serve up 1 billion tweets; it now does that volume every three days. the New York Times’ David Carr likened Twitter to “a river of data.” Still others compare it to a violent gusher. Call it what you will: The tweets will flow with or without you.

Take Ben Smith, the politically engaged editor in chief of the social site BuzzFeed. Smith averages 19.4 daily tweets and uses the information stream to stay in front of each day’s news cycle. For Smith and many like him, Twitter is more than a journalistic tool. “Twitter is not only driving the conversation, it is transforming the design of the modern newsroom,” he says.

But it isn’t just Smith and BuzzFeed that are doubling down on Twitter; newsrooms across the country have bent to the social network’s will. “It’s the best place right now to reach the central opinion makers and that conversation is really where you want to be,” says Smith.

For Ethan Klapper, social media editor, politics, for the Huffington Post, Twitter affords the 22-year-old a peculiar vantage point as he oversees the campaign trail far from the stump speeches and cross-country bus tours.

Klapper, like many young journalists, has been thrust into an elevated position due in part to his fluency monitoring the pulse of the chattering classes via the social medium.

“I often find myself getting home from work and opening up TweetDeck,” Klapper says. In fact, he rarely ventures far from the feed. “When it comes to the real-time news/debate element, Twitter reigns supreme,” the editor says.

...“People on Twitter like the drama of campaigns,” [Republican consultant Vincent] Harris says. “I think that’s why they’re on Twitter. I think they’d be bored if there wasn’t this constant chatter, and I think you’re going to continue seeing campaigns go to Twitter as a means to pick those fights.”

An increasingly hostile environment means more work for campaigns, always struggling to speed their reaction times and dominate the public opinion.

“In 1992, during the Clinton/Gore campaign, the idea of rapid response was responding within the news cycle,” Greenberger points out. “If you got hit at a morning news conference, you have to respond before the evening news. Rapid response is in real-time for the first time. So you have to adjust communications strategy accordingly. The velocity of this is new and it will take people time to adjust.”

With the general election all but officially begun, Zac Moffatt, digital director of the Romney campaign, doesn’t have time to adjust. Moffatt and his team are in unchartered digital territory, and Twitter is but one of their concerns.

Says Moffatt: “I definitely think Twitter has and will have a huge impact on this election, but it has to be recognized that, even with all the talk, even if you had the greatest Twitter strategy out there, I’m not sure you would win on that alone. In fact, I know you wouldn’t.”

...Greenberger tells those involved with campaigns that they must “be committed to tweeting and working on the platform.” Moffatt agrees that a successful Twitter strategy requires serious commitment.

“With the message, you have to make it timely and relevant,” Moffatt says. “If we put out a tweet, it can become the largest driver to our site, and it has become a huge point for us to engage with people.” That level of engagement comes with a price: Promoted trends run roughly $120,000 per day.

That’s hardly a bargain, but the payoff can be enormous. Besides its impact on messaging, Twitter is also becoming an important fundraising tool. “Twitter was a top eight referrer to the Gingrich campaign in terms of where money was being raised,” Harris reports. “For some of my other clients, it is an even more powerful fundraising tool than Facebook.”

Still, as vital as Twitter has become for political campaigns, there is a dark side. For anyone wiling away his days and nights on TweetDeck, fatigue becomes a very real thing, for campaign staffers and journalists alike. In a world routinely grown weary of micro scoops, memes and never-ending political posturing, a social media slipup can mean lost jobs, and lost campaigns.

“There’s so much chance for burnout,” warns Harris. “I think that does scare campaigns. It is terrifying in some ways to think that anyone from my staff or anyone who has access to a campaign Twitter account could instantly tweet out to over 1 million people whatever they want to say. And once it’s out there, it’s out there.”

The issue raises real questions about the restructuring of campaigns in the social media age. Should younger staffers who are more fluent in the medium be handed the reins? Or should senior staffers who can be trusted to stay on message-- and stay out of trouble—be given social media oversight?

Says Harris: “It could be 140 characters that nails the coffin, begging the question: Who do you trust?” Social strategy has become so sensitive, in fact, that the Obama campaign’s digital team refused Adweek’s requests for an interview.

At the end of the day, the position of the campaigns seems to be: Mistakes be damned-- let the information flow. The question is, for how long? “Facebook has become part of the plumbing of the Internet, and I really think Twitter is right on the cusp of doing the same,” says Smith.

The Romney campaign never quite got it and their failure to engage effectively across new media platforms helped create an accurate image of a campaign and a candidate mired in another time and unable to deal authentically with the current concerns of the increasingly large numbers of people who use social media. What started as a GOP advantage and became a Democratic advantage in the 2012 presidential elections may be all evened up now. The buttoned up, top/down authoritarian nature of the Republican Party may not lend itself to ease of Social Media use but the street brawling thuggishness and delusional nature of the teabaggers are custom made for social media in general-- and twitter in particular.