Davey Alba and I led an analysis into 9 popular male podcasters and streamers on YouTube. We reviewed over 1,300 hours of video over the past 2 years to map their guest network and analyzed transcripts to see how they discuss political topics such as voting, transgender identity, war, the economy, medicine, and immigration. Despite framing themselves as non-political — primarily focusing on sports, creator drama, and pranks, they discussed political topics in two-thirds of videos, and their most-booked and most-viewed guests are disproportionately politicians and political pundits.

Watch a video explainer on TikTok
Tips on investigating influencers
Read the methodology
See the data on GitHub

The world's largest crypto casino pays Drake and influencers to promote gambling in livestreams. Lawsuits allege that influencers play with house money and normalize extraordinary wins. I developed a methodology to analyze 500 hours of slots gameplay and estimate win rates for 25 streamers alongside Surya Mattu and Cecilia D'Anastasio. On average, streamers won a jackpot once every 10K spins. Drake and Adin Ross won 4x as frequently as the average when playing the casino's own games. Stake refuted our findings as "categorically incorrect."

Read the Feature
Watch the explainer video

Elena Mejia and I analyzed over two decades of ICE detentions and found migrants were transferred across state lines to ICE facilities along the Southern border at historic rates. In these facilities, our analysis corroborated reporting from Rachel Adams-Heard and Polly Mosendz that legal representation was further away and deportation rates were higher. During the first two months of Trump's second term, we calculated shuttle flights cost taxpayers over $30M.

Read the Deportation Inc. series
See the Data Deportation Project for underlying data

Inspired by an SMS chatbot by MIT researchers, I built a WhatsApp tipline to crowdsource 7,300 screenshots from nearly 900 rideshare drivers in NYC. Natalie Lung, Aaron Gordon, Denise Lu, and I found Uber and Lyft locked drivers out of work every hour of every day in the end of Summer 2024. We found lockouts in the proximity of surge zones, with surges increasing in magnitude in nearly half of cases. We ran financial models to estimate millions at stake for each company if they did not use lockouts to inflate driver statistics to game the city's minimum wage policy. The investigation was cited by city officials and the FTC opened an investigation on the subject. The investigation was a finalist for a Gerald Loeb award for local reporting.

Watch the documentary
Read the methodology
More on crowdsourcing with WhatsApp at GIJN

Recruiters and HR vendors are using AI chatbots to interview and screen job candidates. Davey Alba, Leo Nicoletti, and I found that OpenAI's GPT discriminates against names when ranking resumes. Building off classic hiring and algorithmic bias studies, we randomly assigned demographically-distinct names to equally-qualified resumes and asked GPT-3.5 and 4 to rank the resumes against four real job descriptions. We repeated the experiment 1,000 times, cycling through hundreds of unique names for each job. Differences in how often GPT ranked resumes from each group surpassed benchmarks for adverse impact — a standard used to test for discriminatory hiring practices. The investigation was honored with an ONA Award for Technology reporting.

Watch a video explainer on TikTok
Read the methodology
See the code on GitHub

Aaron Sankin and I found four ISPs charge the same price for drastically different internet speeds based on where you live. In cities across the U.S., neighborhoods that were historically redlined, lower-income, and had the highest concentration of people of color were disproportionately asked to overpay for slow speeds. Building off a technique by Princeton researchers, I found and used undocumented APIs to collect +1M internet plans. I merged socioeconomic data from the U.S. Census and digitized redlining maps. We wrote a story recipe to guide reporters to localized data, and a "Build Your Own Dataset" guide for others to reproduce our study with little-to-no coding. The project was honored with Scripps Howard, SIGMA, NABJ, ONA, SABEW, and Philip Meyer Awards.

Listen to the On The Media interview
Read the methodology
Read my chapter in High Performance Python
See the code on GitHub

My co-author Adrianne Jeffries and I found Amazon gave its own branded products an advantage over better-rated competitors in search results. I trained a random forest to predict which product Amazon placed on top of thousands of popular searches. The investigation was cited by the House antitrust committee in a letter to Amazon, and received a Gerald Loeb Award for personal finance and consumer reporting in 2022. I was lead engineer on Amazon Brand Detector, a Firefox and Chrome extension that helps shoppers spot Amazon branded products.

Download Amazon Brand Detector
Read the methodology
See the code on GitHub

I found an undocumented API and worked with civil rights groups to audit YouTube's in-house brand safety tools. My co-author Aaron Sankin and I found racial justice phrases like Black Lives Matter were blocked, while hate terms like White Lives Matter were not. In fact, we found that YouTube only blocked one-third of well-known hate terms from advertisers. Removing spaces from phrases circumvented the block in almost every instance. In 2022, the series was part of a portfolio honored by NABJ for best practices reporting on algorithmic bias.

Read the hate methodology
Read the social justice methodology
See the code and keywords on GitHub
See Color of Change's petition

I contributed to an ambitious project to distribute a privacy preserving app to collect Facebook data from a national panel. I built the redaction system and data pipelines alongside Micha Gorelick. Alfred Ng and I debunked Facebook's promise to stop Political Group recommendations. Our story was cited by Senator Ed Markey who demanded answers from Facebook for their broken commitments. The project received an Edward R. Murrow Award in Innovation.

Read the methodology
See the top 100 Groups on GitHub

I developed a staining technique to audit Google search results. My reporting partner Adrianne Jeffries and I developed a categorization scheme for all the things found on Google Search. We found Google's own products and answers covered 41% of the first page. Our research was cited in the congressional subcommittee hearing on Big Tech and antitrust. In 2021, "Google the Giant" was a finalist for a Gerald Loeb Award in explanatory journalism.

Read the methodology
A video of Web Assay
See the code on GitHub

Building off Safiya Noble's book, "Algorithms of Oppression: How Search Engines Reinforce Racism", and Latanya Sweeney's, "Discrimination in Online Ad Delivery", I developed an audit of Google Ad's Keyword Planner with my reporting partner Aaron Sankin. We found hundreds of pornographic keyword suggestions for Black, Latina, and Asian girls, but no results whatsoever for "White girls". The story was featured in a NOVA documentary.

Read the article
Videos of related works
See the code on GitHub

Need a random sample of U.S. addresses? Partnered with Big Local News to simplify that process. Now it's easier than ever to get receipts from streets to test for disparate outcomes.

Read why we built this
Try it out

Despite having the largest userbase amongst American adults, YouTube is a social media platform that is often overlooked in academic research. youtube-data-api is a Python client to make this data source more accessible, while introducing new applications and methods to analyze this platform.

ReadTheDocs
GitHub Repo
PyPI Page

urlExpander is a Python package for quickly and thoroughly expanding shortened URLs. Marketing and analytics services like bit.ly are great for tracking engagement. However, these services obfuscate the destination of URLs for social media analysts.

Jupyter Notebook Quickstart
GitHub Repo
PyPI Page