Menus Subscribe Search

Predicting House Races by Weight of Tweet

• October 31, 2012 • 4:00 AM

With the presidential prediction game dreadfully same-y, surely there’s another constantly changing fix for political junkies. How about forecasting all 435 U.S. congressional races every day, based on brand new data every day?

That’s what you get at “Voting With Your Tweet,” an experiment that mines mentions of congressional candidates in the Twitter-sphere to predict who will win each race and what the actual vote share will be. Unlike past efforts at using social media to predict political contests, which made their “predictions” after the voters had settled the matter, this research is happening now and you can check in at the California News Service site to see what’s up today, yesterday, or tomorrow.

Using social media as a forecasting tool is a hot area right now, and mixing Twitter with punditry is not brand new. Carnegie Mellon’s Brendan O’Connor compared tweeting to polling results in 2010, and not surprisingly found some correlation. Andranik Tumasjan and his colleagues at the Munich Technical University found that “the mere number of messages mentioning a party reflects the election result” in a German federal election. The “media utility” Tweetminster, meanwhile, says it accurately predicted the outcome of the last British Parliamentary elections using Twitter (an experiment they note is based on an earlier Japanese study looking at “online buzz and election results”).

Voting With Your Tweet is a kind of combination, using past results to predict future returns (but with mountains of caveats).

Analyzing about a quarter million tweets from 356 races in the 2010 mid-terms, UC Berkeley doctoral candidate Mark Huberty correctly “predicted” (after the fact) the winners 92 percent of the time, a much better showing than the six professional human pundits used for comparison. (The technical report on 2010 is available here, but be prepared to see that the 92 percent figure is one of a number of outcomes based on different statistical methods and statistical approaches. Huberty goes with “better than 85 percent accuracy” in the paper’s introduction.)

Taking that information, Huberty “trained two machine learning algorithms to determine what word features of those tweets best predicted whether the Democratic or Republican party candidate won each race.” So in its current incarnation …

We think the finished algorithm works like this:

First, it identifies from the language in a candidate’s tweets whether they are the incumbent or challenger. Since incumbents win about 85% of the time, this provides a good baseline.

It then adjusts the baseline prediction based on sentiment and action-related phrases. For instance, “voted hcr” (indicating that the incumbent voted for health care reform) was one of the most influential predictors alongside incumbency-related phrases. The algorithm weights those phrases positively or negatively, depending on how predictive they were of a candidate winning or losing.

And you can take this forecast to the bank? Only if you’re Lehman Brothers. “Voting with your Tweet is an experiment and should be treated as such,” Huberty and “data guru” Len DeGroot from the Knight Digital Media Center at Berkeley’s Graduate School of Journalism write in an honest and detailed set of FAQs. “We think this might work and think we might know why. But we could fail spectacularly.”

So why do it at all, or at least so publicly? The answers are refreshing:

Anyone who is interested can observe the experiment.
It keeps us honest: whether we succeed or fail, the predictions will be out there for all to see.
Observers can offer constructive feedback.
It gives us the opportunity post our own observations.
It offers the general public a window into the intersection of social data and political research.

So knowing this, I peeked at the putative winners for some races I’m following, starting with the competitive bout between Democratic incumbent Lois Capps and challenger Abel Maldonado in California’s 24th, Pacific Standard’s home turf. As of last night, VWYT gives it to Maldonado, with 53 percent of the vote.

Then there’s Berman-Sherman, the heated race between two Democratic incumbents battling for a single seat in LA? Ah nothing, not even Brad Sherman’s name, since the algorithm only codes for races with a Republican-Democratic contest.

OK, how about Kansas’s 2nd, the district where my mom is buried? (Kansas not being Chicago or Louisiana, Mom can’t vote there.) Incumbent Republican Lynn Jenkins is shellacking Tobias Schlingensiepen with a 65 percent prediction. That’s not surprising in this very blue state, but I wonder if the challenger’s name isn’t a bit Twitter-unfriendly.

As suggested, Huberty and co. see lots of ways this experiment can go pear-shaped, many of the potential problems hinging on using 2010 results to craft important topic choices this year. The mid-terms, after all, saw a powerful effort by Tea Party partisans, which could mean the terms over-represent Republican memes and challengers’ chops. Plus, there are new issues in the mix now, such as Libya and Solyndra.

Nonetheless, it’s fun to see political science in action and even better that for once it’s not about those two guys running for president.

Michael Todd
Most of Michael Todd's career has been spent in newspaper journalism, ranging from papers in the Marshall Islands to tiny California farming communities. Before joining the publishing arm of the Miller-McCune Center, he was managing editor of the national magazine Hispanic Business.

More From Michael Todd

A weekly roundup of the best of Pacific Standard and PSmag.com, delivered straight to your inbox.

Recent Posts

September 2 • 4:00 PM

Professors’ Pet Peeves

Ten things to avoid in your classrooms this year.


September 2 • 2:00 PM

Music Lessons Enhance Brain Function in Disadvantaged Kids

Children from poor neighborhoods in Los Angeles who took regular music lessons for two years were able to distinguish similar speech sounds faster than their peers.


September 2 • 12:00 PM

California Passes a Bill to Protect Workers in the Rapidly Growing Temp Staffing Industry

The bill will hold companies accountable for labor abuses by temp agencies and subcontractors they use.


September 2 • 10:00 AM

SWAT Pranks and SWAT Mistakes

The proliferation of risky police raids over the decades.


September 2 • 9:12 AM

Conference Call: The Graphic Novel


September 2 • 8:00 AM

Why We’re Not Holding State Legislators Accountable

The way we vote means that the political fortunes of state legislators hinge on events outside of their state and their control.


September 2 • 7:00 AM

When Men Who Abstain From Premarital Sex Get Married

Young men who take abstinence pledges have trouble adjusting to sexual norms when they become husbands.


September 2 • 6:00 AM

The Rise of Biblical Counseling

For millions of Christians, biblical counselors have replaced psychologists. Some think it’s time to reverse course.


September 2 • 5:12 AM

No Innovation Without Migration

People bring their ideas with them when they move from place to place.


September 2 • 4:00 AM

Why Middle School Doesn’t Have to Suck

Some people suspect the troubles of middle school are a matter of age. Middle schoolers, they think, are simply too moody, pimply, and cliquish to be easily educable. But these five studies might convince you otherwise.


September 2 • 3:13 AM

Coming Soon: When Robots Lie


September 2 • 2:00 AM

Introducing the New Issue of ‘Pacific Standard’

The science of self-control, the rise of biblical counseling, why middle school doesn’t have to suck, and more in our September/October 2014 print issue.


September 1 • 1:00 PM

Television and Overeating: What We Watch Matters

New research finds fast-moving programming leads to mindless overeating.



September 1 • 6:00 AM

Why Someone Named Monty Iceman Sold Doogie Howser’s Estate

How unusual names, under certain circumstances, can lead to success.



August 29 • 4:00 PM

The Hidden Costs of Tobacco Debt

Even when taxpayers aren’t explicitly on the hook, tobacco bonds can cost states and local governments money. Here’s how.


August 29 • 2:00 PM

Why Don’t Men and Women Wear the Same Gender-Neutral Bathing Suits?

They used to in the 1920s.


August 29 • 11:48 AM

Your Brain Decides Whether to Trust Someone in Milliseconds

We can determine trustworthiness even when we’re only subliminally aware of the other person.


August 29 • 10:00 AM

True Darwinism Is All About Chance

Though the rich sometimes forget, Darwin knew that nature frequently rolls the dice.


August 29 • 8:00 AM

Why Our Molecular Make-Up Can’t Explain Who We Are

Our genes only tell a portion of the story.


August 29 • 6:00 AM

Strange Situations: Attachment Theory and Sexual Assault on College Campuses

When college women leave home, does attachment behavior make them more vulnerable to campus rape?


August 29 • 4:00 AM

Forgive Your Philandering Partner—and Pay the Price

New research finds people who forgive an unfaithful romantic partner are considered weaker and less competent than those who ended the relationship.


August 28 • 4:00 PM

Some Natural-Looking Zoo Exhibits May Be Even Worse Than the Old Concrete Ones

They’re often designed for you, the paying visitor, and not the animals who have to inhabit them.


August 28 • 2:00 PM

What I Learned From Debating Science With Trolls

“Don’t feed the trolls” is sound advice, but occasionally ignoring it can lead to rewards.


Follow us


Subscribe Now

When Men Who Abstain From Premarital Sex Get Married

Young men who take abstinence pledges have trouble adjusting to sexual norms when they become husbands.

Your Brain Decides Whether to Trust Someone in Milliseconds

We can determine trustworthiness even when we’re only subliminally aware of the other person.

Young, Undocumented, and Invisible

While young migrant workers struggle under poor working conditions, U.S. policy has done little to help.

Education, Interrupted

When it comes to educational access, young Syrian refugees are becoming a “lost generation.”

No, Smartphone-Loss Anxiety Disorder Isn’t Real

But people are anxious about losing their phones, even if they don’t do much to protect them.

The Big One

One third of the United States federal budget for fighting wildfires goes toward one percent of such fires. September/October 2014 big-one-fires-final

Copyright © 2014 by Pacific Standard and The Miller-McCune Center for Research, Media, and Public Policy. All Rights Reserved.