How a young developer stumbled in to journalism and landed at FiveThirtyEight

Dhrumil Mehta

On Friday, FiveThirtyEight announced that Dhrumil Mehta (a former Knight Lab student fellow) would be joining their team as a database journalist. It was fun news for us to hear, particularly when you consider that a year and half ago journalism wasn’t even a small part Mehta’s career plan.

At the time, Mehta was a senior here at Northwestern and six months from completing a bachelor’s degree in philosophy (with a cognitive science minor) and a master’s degree in computer science.

As a student, he'd built a few websites for non-profits and civic organizations, but he wasn’t quite sure how to take his technical skills and apply them to a job he really cared about.

“I had always felt out of place in computer science,” Mehta said. “I always liked making things, but I didn’t enjoy making just anything. I wanted to do something to make people’s lives better.”

At the time, he talked frequently about following the well-worn computer science graduate’s path from school to big West Coast technology firms — Microsoft, Amazon, Oracle, etc. — before finding a way to do work he really loved.

And then he joined the Lab as a fellow, he worked on a few projects, and joined the team for the trip to NICAR's 2013 conference in Louisville. And attending the NICAR conference, it turned out, would make all the difference.

“What was most striking to me was the casual manner in which journalists at NICAR spoke about the truly huge impact that they were having on the world,” he wrote at the time, “and how powerful use of data can be in showing the vastness of any given problem and spurring people to act to resolve it.”

At NICAR, he said, he found people he wanted to be and be like.

He also caught the interest of USA Today’s Paul Overberg and Jodi Upton, who could see the potential in an academic project Mehta had been working on to become a useful new news app.

The political rhetoric project

Inspired by the linguist George Lakoff and his books Metaphors We Live By and Political Mind, Mehta started to think about how politicians use metaphors to frame political topics in speeches. He wondered if he could use data and natural language processing to figure out not only how politicians frame certain topics, but how they frame topics given party affiliation, and how framing changes over time.

(NOTE: There’s a fair amount of detail down below, but also check out the project’s blog and the academic abstract.)

Working with congressional speech data from the Sunlight Foundation’s Capitol Words project, he built an algorithm that analyzed 10,000 speeches in each of seven categories: national deficit, foreign policy, healthcare, immigration, marriage, the Middle East, and Social Security.

Using a TF/IDF weighted multinomial naïve Bayes classifier (commonly used to filter spam), he found that he could reliably classify a both a speech’s category and the party of the speech giver.

It was an interesting project, but Mehta wasn’t content to merely classify speeches. Instead he fed the classifier a set of rhetorical frames culled from WordNet, a lexical database of English words that are grouped into sets of “cognitive synonyms (synsets), each expressing a distinct concept.”

Mehta used Wordnet’s synsets to build 500-word frames related to specific topics: Christianity, crime, finance, sex, and military.

The idea was to figure out if a particular frame was present in the rhetoric of the seven categories he’d chosen (national deficit, immigration, etc.). So instead of feeding the classifier new speeches, he fed it frames.

He found that words from particular frames were highly correlated with speeches about particular topics. For example, he found speeches on immigration often included words related to crime.

Congressional speeches in which a particular rhetorical frame is present. Credit: Dhrumil Mehta

Digging deeper (and with the help of a binomial classifier trained only on immigration speeches) he found that Republicans used crime rhetoric much more often than Democrats when talking about immigration.

Though the project was academic, it caught the interest of Overberg and Upton who Mehta met at NICAR 13.

Together, they began thinking about how Political Framing might go from an academic project to a functional news app that would help journalists find news.

What if, for example, Political Framing could show you when a party’s — or politician’s — rhetoric on a certain issue changed? Could Political Framing cross-reference changes in speech with campaign contribution data to alert reporters to a rhetorical change following a large campaign contribution?

Last week, Mehta and his teammate (and current student fellow) Al Johri, took the first step toward finding out with, which seeks to help reporters find trends in congressional rhetoric. They’re currently looking for alpha testers.

Meanwhile, real life

Despite the interest in Political Framing and taking significant detours in to journalism and civic technology — an internship at the Berkman Center for Internet & Society at Harvard University, to name one — he also managed to graduate and land an engineering job and moved to Seattle last fall.

But journalism and his civic technology projects kept pulling. Political Framing, in particular, “turned out to be something much bigger than I thought it would be,” he said.

He presented his work on the project at NICAR 2014 and will do the same at the American Political Science Association’s conference later this year.

He also happened to see a job earlier this year on the NICAR-L listserv that proved irresistible, "database journalist, politics." He reached out to Andrei Scheinkman, deputy editor and director of data and technology at FiveThirtyEight, about the position and was eventually hired.

Despite his accomplishments, journalism is a new track for Mehta.

“I’m totally new to journalism,” Mehta said. “I’m really nervous and excited at the same time.”

In the end, the big tech firm job was nice, but his heart wasn't in it.

“It may sound simple but I wanted to do something that is good for people,” he said.

About the author

Ryan Graff

Communications and Outreach Manager, 2011-2016

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

Latest Posts

  • Building a Community for VR and AR Storytelling

    In 2016 we founded the Device Lab to provide a hub for the exploration of AR/VR storytelling on campus. In addition to providing access to these technologies for Medill and the wider Northwestern community, we’ve also pursued a wide variety of research and experimental content development projects. We’ve built WebVR timelines of feminist history and looked into the inner workings of ambisonic audio. We’ve built virtual coral reefs and prototyped an AR experience setting interviews...

    Continue Reading

  • A Brief Introduction to NewsgamesCan video games be used to tell the news?

    When the Financial Times released The Uber Game in 2017, the game immediately gained widespread popularity with more than 360,000 visits, rising up the ranks as the paper’s most popular interactive piece of the year. David Blood, the game’s lead developer, said that the average time spent on the page was about 20 minutes, which was substantially longer than what most Financial Times interactives tend to receive, according to Blood. The Uber Game was so successful that the Financial...

    Continue Reading

  • With the 25th CAR Conference upon us, let’s recall the first oneWhen the Web was young, data journalism pioneers gathered in Raleigh

    For a few days in October 1993, if you were interested in journalism and technology, Raleigh, North Carolina was the place you had to be. The first Computer-Assisted Reporting Conference offered by Investigative Reporters & Editors brought more than 400 journalists to Raleigh for 3½ days of panels, demos and hands-on lessons in how to use computers to find stories in data. That seminal event will be commemorated this week at the 25th CAR Conference, which...

    Continue Reading

  • Prototyping Augmented Reality

    Something that really frustrates me is that, while I’m excited about the potential AR has for storytelling, I don’t feel like I have really great AR experiences that I can point people to. We know that AR is great for taking a selfie with a Pikachu and it’s pretty good at measuring spaces (as long as your room is really well lit and your phone is fully charged) but beyond that, we’re really still figuring...

    Continue Reading

  • Capturing the Soundfield: Recording Ambisonics for VR

    When building experiences in virtual reality we’re confronted with the challenge of mimicking how sounds hit us in the real world from all directions. One useful tool for us to attempt this mimicry is called a soundfield microphone. We tested one of these microphones to explore how audio plays into building immersive experiences for virtual reality. Approaching ambisonics with the soundfield microphone has become popular in development for VR particularly for 360 videos. With it,...

    Continue Reading

  • Audience Engagement and Onboarding with Hearken Auditing the News Resurrecting History for VR Civic Engagement with City Bureau Automated Fact Checking Conversational Interface for News Creative Co-Author Crowdsourcing for Journalism Environmental Reporting with Sensors Augmented Reality Visualizations Exploring Data Visualization in VR Fact Flow Storytelling with GIFs Historical Census Data Information Spaces in AR/VR Contrasting Forms Of Interactive 3D Storytelling Interactive Audio Juxtapose Legislator Tracker Storytelling with Augmented Reality Music Magazine Navigating Virtual Reality Open Data Reporter Oscillations Personalize My Story Photo Bingo Photojournalism in 3D for VR and Beyond Podcast Discoverability Privacy Mirror Projection Mapping ProPublica Illinois Rethinking Election Coverage SensorGrid API and Dashboard Sidebar Smarter News Exploring Software Defined Radio Story for You Storyline: Charts that tell stories. Storytelling Layers on 360 Video Talking to Data Visual Recipes Watch Me Work Writing and Designing for Chatbots
  • Prototyping Spatial Audio for Movement Art

    One of Oscillations’ technical goals for this quarter’s Knight Lab Studio class was an exploration of spatial audio. Spatial audio is sound that exists in three dimensions. It is a perfect complement to 360 video, because sound sources can be localized to certain parts of the video. Oscillations is especially interested in using spatial audio to enhance the neuroscientific principles of audiovisual synchrony that they aim to emphasize in their productions. Existing work in spatial......

    Continue Reading

Storytelling Tools

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

View More