Articles by Brandon Roberts

• JournalismAI Discovery

  

  I wrote a newsletter-based introductory course for the London School of Economics about AI and how it's used within journalism.

• Datasette Powered Investigative Journalism

  

  Tips for using Datasette for investigative projects

• Journalistic Tools Fast: Declarative Programming with Htmx and Hyperscript

  I explore two web-based declarative languages & tools that allow me to build one-off utilities that greatly speed up my investigative process

• nextLI's Google News Initiative Innovation Challenge (2021)

  

  As part of Newsday's GNI Innovation Challenge, I extended Datasette and built plugins to improve its usability within the newsroom.

• Investigating Washington State police departments & sheriffs ... Problems with HB-1888

  

  I'm announcing an investigative data project involving police and sheriffs offices misconduct. But I'm running into issues with a new state privacy law, preventing speedy access to public information.

• Investigating Vancouver Police Department's deadly use of force

  

  In collaboration with Troy Brynelson of Oregon Public Broadcasting, I investigated Vancouver Police Department's relatively high number of deadly shootings.

• ProPublica's Electionland (2020)

  

  I made it easier for reporters to monitor for voting issues during the 2020 general election.

• The Membership Guide

  

  I got an opportunity to make WordPress shine.

• Nonprofit Explorer

  

  I made ProPublica's flagship news application easier to read, search and maintain

• Collaborate

  

  With ProPublica I developed Collaborate - An open source tool to ease the process of gathering tips from the public and sharing them between newsrooms.

• Dissecting a Machine Learning Powered Investigation

  

  Uncovering local property tax evasion using machine learning and statistical modeling. An investigative recipe.

• Rethinking Web Scraping with AutoScrape

  Web scraping is tedious. In this article, I explore patterns for building scrapers and introduce a new tool, AutoScrape.

• Robust Web Scraping in the Public Interest with AutoScrape (Research Paper)

  Presented to Computation + Journalism 2019

• AutoScrape: Robust Web Scraping in the Public Interest

  

  Presented to Computation + Journalism 2019 and detailed in Artificial Informer

• Extracting References from Political Auto-Transcripts (Research Paper)

  

  Presented to Data Science + Journalism Workshop at KDD 2017