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

November 25 • 4:00 PM

Is the Federal Reserve Bank of New York Doing Enough to Monitor Wall Street?

Bank President William Dudley says supervision is stronger than ever, but Democratic senators are unconvinced: “You need to fix it, Mr. Dudley, or we need to get someone who will.”


November 25 • 3:30 PM

Cultural Activities Help Seniors Retain Health Literacy

New research finds a link between the ability to process health-related information and regular attendance at movies, plays, and concerts.


November 25 • 12:00 PM

Why Did Doctors Stop Giving Women Orgasms?

You can thank the rise of the vibrator for that, according to technology historian Rachel Maines.


November 25 • 10:08 AM

Geography, Race, and LOLs

The online lexicon spreads through racial and ethnic groups as much as it does through geography and other traditional linguistic measures.


November 25 • 10:00 AM

If It’s Yellow, Seriously, Let It Mellow

If you actually care about water and the future of the species, you’ll think twice about flushing.


November 25 • 8:00 AM

Sometimes You Should Just Say No to Surgery

The introduction of national thyroid cancer screening in South Korea led to a 15-fold increase in diagnoses and a corresponding explosion of operations—but no difference in mortality rates. This is a prime example of over-diagnosis that’s contributing to bloated health care costs.



November 25 • 6:00 AM

The Long War Between Highbrow and Lowbrow

Despise The Avengers? Loathe the snobs who despise The Avengers? You’re not the first.


November 25 • 4:00 AM

Are Women More Open to Sex Than They Admit?

New research questions the conventional wisdom that men overestimate women’s level of sexual interest in them.


November 25 • 2:00 AM

The Geography of Innovation, or, Why Almost All Japanese People Hate Root Beer

Innovation is not a product of population density, but of something else entirely.


November 24 • 4:00 PM

Federal Reserve Announces Sweeping Review of Its Big Bank Oversight

The Federal Reserve Board wants to look at whether the views of examiners are being heard by higher-ups.



November 24 • 2:00 PM

That Catcalling Video Is a Reminder of Why Research Methods Are So Important

If your methods aren’t sound then neither are your findings.


November 24 • 12:00 PM

Yes, Republicans Can Still Win the White House

If the economy in 2016 is where it was in 2012 or better, Democrats will likely retain the White House. If not, well….


November 24 • 11:36 AM

Feeling—Not Being—Wealthy Cuts Support for Economic Redistribution

A new study suggests it’s relative wealth that leads people to oppose taxing the rich and giving to the poor.


November 24 • 10:00 AM

Why Are Patients Drawn to Certain Doctors?

We look for an emotional fit between our physicians and ourselves—and right now, that’s the best we can do.


November 24 • 8:00 AM

Why Do We Elect Corrupt Politicians?

Voters, it seems, are willing to forgive—over and over again—dishonest yet beloved politicians if they think the job is still getting done.



November 24 • 6:00 AM

They Steal Babies, Don’t They?

Ethiopia, the Hague, and the rise and fall of international adoption. An exclusive investigation of internal U.S. State Department documents describing how humanitarian adoptions metastasized into a mini-industry shot through with fraud, becoming a source of income for unscrupulous orphanages, government officials, and shady operators—and was then reined back in through diplomacy, regulation, and a brand-new federal law.


November 24 • 4:00 AM

Nudging Drivers, and Pedestrians, Into Better Behavior

Daniel Pink’s new series, Crowd Control, premieres tonight on the National Geographic Channel.


November 21 • 4:00 PM

Why Are America’s Poorest Toddlers Being Over-Prescribed ADHD Drugs?

Against all medical guidelines, children who are two and three years old are getting diagnosed with ADHD and treated with Adderall and other stimulants. It may be shocking, but it’s perfectly legal.



November 21 • 2:00 PM

The Best Moms Let Mess Happen

That’s the message of a Bounty commercial that reminds this sociologist of Sharon Hays’ work on “the ideology of intensive motherhood.”


November 21 • 12:00 PM

Eating Disorders Are Not Just for Women

Men, like women, are affected by our cultural preoccupation with thinness. And refusing to recognize that only makes things worse.


November 21 • 10:00 AM

Queens of the South

Inside Asheville, North Carolina’s 7th annual Miss Gay Latina pageant.


Follow us


Geography, Race, and LOLs

The online lexicon spreads through racial and ethnic groups as much as it does through geography and other traditional linguistic measures.

Feeling—Not Being—Wealthy Cuts Support for Economic Redistribution

A new study suggests it's relative wealth that leads people to oppose taxing the rich and giving to the poor.

Sufferers of Social Anxiety Disorder, Your Friends Like You

The first study of friends' perceptions suggest they know something's off with their pals but like them just the same.

Standing Up for My Group by Kicking Yours

Members of a minority ethnic group are less likely to express support for gay equality if they believe their own group suffers from discrimination.

How Old Brains Learn New Tricks

A new study shows that the neural plasticity needed for learning doesn't vanish as we age—it just moves.

The Big One

One in two United States senators and two in five House members who left office between 1998 and 2004 became lobbyists. November/December 2014

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