Menus Subscribe Search

Follow us


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

October 20 • 4:00 PM

The Bird Hat Craze That Sparked a Preservation Movement

How a fashion statement at the turn of the 19th century led to the creation of the first Audubon societies.


October 20 • 2:00 PM

The Risk of Getting Killed by the Police If You Are White, and If You Are Black

An analysis of killings by police shows outsize risk for young black males.


October 20 • 12:00 PM

Love and Hate in Israel and Palestine

Psychologists find that parties to a conflict think they’re motivated by love while their enemies are motivated by hate.


October 20 • 11:00 AM

My Dog Comes First: The Importance of Pets to Homeless Youth

Dogs and cats have both advantages and disadvantages for street-involved youth.


October 20 • 10:00 AM

Homophobia Is Not a Thing of the Past

Despite growing support for LGBT rights and recent decisions from the Supreme Court regarding the legality of same-sex marriage, the battle for acceptance has not yet been decided.


October 20 • 8:00 AM

Big Boobs Matter Most

Medical mnemonics are often scandalous and sexist, but they help the student to both remember important facts and cope with challenging new experiences.


October 20 • 6:00 AM

When Disease Becomes Political: The Likely Electoral Fallout From Ebola

Will voters blame President Obama—and punish Democrats in the upcoming mid-term elections—for a climate of fear?


October 20 • 4:00 AM

Coming Soon: The Anatomy of Ignorance


October 17 • 4:00 PM

What All Military Families Need to Know About High-Cost Lenders

Lessons from over a year on the beat.


October 17 • 2:00 PM

The Majority of Languages Do Not Have Gendered Pronouns

A world without “he.” Or “she.”


October 17 • 11:01 AM

How to Water a Farm in Sandy Ground

Physicists investigate how to grow food more efficiently in fine-grained soil.


October 17 • 10:00 AM

Can Science Fiction Spur Science Innovation?

Without proper funding, the answer might not even matter.


October 17 • 8:00 AM

Seattle, the Incredible Shrinking City

Seattle is leading the way in the micro-housing movement as an affordable alternative to high-cost city living.


October 17 • 6:00 AM

‘Voodoo Death’ and How the Mind Harms the Body

Can an intense belief that you’re about to die actually kill you? Researchers are learning more about “voodoo death” and how it isn’t limited to superstitious, foreign cultures.


October 17 • 4:00 AM

That Arts Degree Is Paying Off

A survey of people who have earned degrees in the arts find they are doing relatively well, although their education didn’t provide much guidance on managing a career.


October 16 • 4:00 PM

How (Some) Economists Are Like Doomsday Cult Members

Cognitive dissonance and clinging to paradigms even in the face of accumulated anomalous facts.


October 16 • 2:00 PM

The Latest—and Most Mysterious—Player in the Nasty Battle Over Net Neutrality

As the FCC considers how to regulate Internet providers, the telecom industry’s stealth campaign for hearts and minds encompasses everything from art installations to LOLcats.


October 16 • 12:00 PM

How Many Ads Is Too Many Ads?

The conundrum of online video advertising.


October 16 • 11:00 AM

Unlocking Consciousness

A study of vegetative patients closes in on the nature of consciousness.


October 16 • 10:00 AM

The False Promises of Higher Education

Danielle Henderson spent six years and $60,000 on college and beyond. The effects of that education? Not as advertised.


October 16 • 8:00 AM

Faster Justice, Closer to Home: The Power of Community Courts

Community courts across the country are fighting judicial backlog and lowering re-arrest rates.


October 16 • 6:00 AM

Killing Your Husband to Save Yourself

Without proper legal instruments, women with abusive partners are often forced to make a difficult choice: kill or be killed.


October 16 • 4:00 AM

Personality Traits Linked to Specific Diseases

New research finds neurotic people are more likely to suffer a serious health problem.


October 16 • 2:00 AM

Comparing Apples to the Big Apple: Yes, Washington, D.C., Is More Expensive Than New York City

Why shouldn’t distant locales tied to jobs in the urban core count in a housing expenditure study?


October 15 • 4:00 PM

Why Asian American Parents Are the Least Likely to Spank Their Kids

Highly educated, middle-class parents are less likely to use corporal punishment to discipline their children than less-educated, working-class, and poor parents.


Follow us


Love and Hate in Israel and Palestine

Psychologists find that parties to a conflict think they're motivated by love while their enemies are motivated by hate.

How to Water a Farm in Sandy Ground

Physicists investigate how to grow food more efficiently in fine-grained soil.

Unlocking Consciousness

A study of vegetative patients closes in on the nature of consciousness.

Advice for Emergency Alert Systems: Don’t Cry Wolf

A survey finds college students don't always take alerts seriously.

Brain’s Reward Center Does More Than Manage Rewards

Nucleus accumbens tracks many different connections in the world, a new rat study suggests.

The Big One

One company, Amazon, controls 67 percent of the e-book market in the United States—down from 90 percent five years ago. September/October 2014 new-big-one-5

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