TweetCast knows (probably) who gets your vote

Today the Knight Lab quietly took the wraps off a project that seeks to uncover a secret most Americans hold — who we plan to vote for in this week’s presidential election.

The project, Tweet Cast Your Vote (, is experimental, but accurately predicts the candidate Twitter users plan to vote for up to 80 percent of the time.

For now the tool is an interesting experience for the user — a sort of political Guess Your Weight game. But the strategy and algorithms behind the tool are a whole other level of awesome.

“The technology observes people on Twitter who we know support Obama or Romney and runs algorithms that find patterns in their Twitter activity,” said Shawn O’Banion, a Northwestern University Ph.D. student who created the technology with Larry Birnbaum, a Knight Lab co-founder and professor of computer science at the McCormick School of Engineering.

“That initial observation allows us to predict the behavior of ‘unknowns,’ or users who we have not already observed and who we do not know to be on one side or the other,” O’Banion said.

Specifically the technology tracks words, @-mentions, hashtags and links in the Twitter feeds of known political supporters and compares those to the same elements in the feeds of other potential voters. The greater the similarity between the two, the more likely they are to support the same candidate, O’Banion said.

The system is most accurate — about 80 percent — with users who tweet about political issues. It’s less accurate — about 65 percent — with users who aren’t obviously political, O’Banion said.

A variety of factors lead to TweetCast’s miscalculations, but the biggest is sample size. It’s difficult to find users known to support a specific candidate and a larger sample size would improve the system’s accuracy, he said.

Apart from a more robust sample, other avenues could be used to improve the technology — using TweetCast’s user feedback system to fine tune results, for example, or by including other sources of data from Twitter like favorited tweets, or a user’s network of followers.

Though the technology is an intriguing capability demonstration at the moment, it’s easy to see its practical application — either in helping to predict the outcome of an election, or in targeting political advertising to undecided voters.

Imagine how much the Romney or Obama campaigns would like to do that.

The Knight Lab isn't the only group interested in finding political persuasions in Twitter data. We  were excited to see that a similar project launched just this week: Prez-O-Meter by SwiftKey.

“I'm impressed with SwiftKey's work,” O’Banion said. “I particularly like how they show you where on the ‘spectrum’ of political ideology you fall. The main difference between our work and theirs is that while they are comparing you to the candidates themselves, we compare you to other, normal Twitter users that we know support either Obama or Romney.”

TweetCast’s approach is unique “because it can learn patterns that may be useful in predicting political preference, such as hobbies, interests, religious practices, etc.” that aren’t directly tied to politics, O’Banion said.

Check out both projects. And be sure to let us know how TweetCast works for you.

TweetCast is part of the Knight Lab’s Social Loupe Projects — which includes twxRay and HashTagger — that seek to find meaning and utility in social media data.

Also, a special thanks to Medill’s Jeremy Gilbert and our own Miranda Mulligan for stepping up and helping Shawn develop TweetCast’s front end.

About the author

Ryan Graff

Journalism, revenue, whitewater, former carny. Recently loving some quality time @KelloggSchool.

Latest Posts

  • A Google Spreadsheets change affecting TimelineJS users

    Google recently changed something about their Sheets service which is causing many people to run into an error when they are making a new timeline. Note: there should be no impact on existing timelines! After this change, many of you click on the "preview" and get this message: An unexpected error occurred trying to read your spreadsheet data [SyntaxError] Timeline configuration has no events. There is a straightforward work-around, but it requires those of you who have...

    Continue Reading

  • How Americans think and feel about gun violence

    A man killed his wife, then himself. I want you to see his face and learn that he enjoyed fishing with his grandchildren. A small-time drug dealer is shot by two men in a parking lot. I find his Facebook profile and a photo shows him striking a playfully irreverent pose, giving the camera the middle finger. The photo’s comments take a mournful turn after a certain date. “Rest easy bro ???” Gun Memorial runs...

    Continue Reading

  • Software developers interested in journalism: Northwestern and The Washington Post want you!

    Northwestern University and The Washington Post are offering a unique opportunity for two talented software developers interested in applying their programming skills in media and journalism. Here’s the proposition: (1) a full-tuition scholarship to earn a master’s degree in journalism at Northwestern University, followed by (2) a six-month paid internship with The Post’s world-class engineering team, with the possibility of subsequent full-time employment. These opportunities are made possible by the John S. and James L....

    Continue Reading

  • What happened when Gun Memorial let anyone contribute directly to victim profiles

    If you’re reporting local or niche news, there’s a good chance that your audience collectively knows more about the story than you do. That’s especially true for us at Gun Memorial, a small publication with a nationwide mission of covering every American who is shot dead. In our latest, mostly successful, experiment, we let readers add to our stories without editor intervention. This article shares some lessons from that experience. Asking for reader contributions A...

    Continue Reading

  • How conversational interfaces make the internet more accessible for everyone

    This story is part of a series on bringing the journalism we produce to as many people as possible, regardless of language, access to technology, or physical capability. Find the series introduction, as well as a list of published stories here. In 2004, human-computer interaction professor Alan Dix published the third edition of Human-Computer Interaction along with his colleagues, Janet Finley, Gregory Abowd, and Russell Beale. In a chapter called “The Interaction,” the authors wrote...

    Continue Reading

  • Three tools to help you make colorblind-friendly graphics

    This story is part of a series on bringing the journalism we produce to as many people as possible, regardless of language, access to technology, or physical capability. Find the series introduction, as well as a list of published stories here. I am one of the 8% of men of Northern European descent who suffers from red-green colorblindness. Specifically, I have a mild case of protanopia (also called protanomaly), which means that my eyes lack...

    Continue Reading

Storytelling Tools

We build easy-to-use tools that can help you tell better stories.

View More