Fact Flow

Efficiency for editing. Credibility and trust for publishing

Editorial fact-checking is a mess at best and readers don't see the benefits. Typically they doubt it happens or don't appreciate the work it takes to make it happen. On the editing side, almost everyone who does it uses an antiquated process derived from print production habits even though most writers and editors are drafting in Google Docs. This can be better. Let's make it better for both editorial and readers!

Faculty and Staff Leads

Kris Hammond

Professor of Electrical Engineering and Computer Science

Prior to joining the faculty at Northwestern, Kris founded the University of Chicago’s Artificial Intelligence Laboratory. His research has been primarily focused on artificial intelligence, machine-generated content and context-driven information systems. Kris currently sits on a United Nations policy committee run by the United Nations Institute for Disarmament Research (UNIDIR). He received his PhD from Yale.

Joe Germuska

Chief Nerd

Joe runs Knight Lab’s technology, professional staff and student fellows. Before joining us, Joe was on the Chicago Tribune News Apps team. He is the founder of CensusReporter.org, and a proud board member of City Bureau.

Zach Wise

Professor, Journalism

Emmy winning interactive producer & Associate Professor @NorthwesternU, @KnightLab. Formerly of The New York Times. Creator of TimelineJS & StoryMapJS

Project Details

2019 Spring
Fact Flow

Description

Editorial fact-checking is a mess at best and readers don't see the benefits. Typically they doubt it happens or don't appreciate the work it takes to make it happen. On the editing side, almost everyone who does it uses an antiquated process derived from print production habits even though most writers and editors are drafting in Google Docs. This can be better. Let's make it better for both editorial and readers!

Important Questions
  • How do writers and editors work through making sure stories are as accurate as possible?
  • How can we integrate more efficient fact-checking into existing workflows?
  • How might we make the details of the fact-checking useful to readers without cluttering or distracting?
  • How can we surface fact-checking from the workflow to readers to address transparency, credibility and trust?
Sample Milestones
  • Design a clean user-interface for authors and editors to manage checking facts for a story in Google Docs.
  • Design thinking and ideation about how the fact-check "metadata" could be published or adapted for the audience.
Outcome

Several teams will work on building a Google Docs plugin that facilitates effecient fact-checking based on design research that has been done in previous iterations of the project and from new design research conducted by the team. One or more teams will prototype a published version of the fact-checked content for user-testing. The goal is to determine the effect of surfacing contextual fact-checked information on the reading experience and the reader's sense of credibility and trust.

2018 Spring
Factchecking Flow

Description

While Artificial Intelligence is all the buzz, there are a lot of opportunities for technology that augments human intelligence instead of replacing it. An important but time-consuming part of editorial review is verifying all facts in a story. Is there a way we can augment the capabilities of writers and editors to make this work faster and better? Building upon promising results in the Winter edition of the studio class, we will continue developing a system which makes humans more effective in this phase of publishing a story. This project will be a combination of theory and practice: the focus will be on developing a functional system that is as ready for release as possible, but we will keep our eyes out for "stretch" opportunities and invest some time exploring how they might take shape.

Important Questions
  • How do writers and editors work through making sure stories are as accurate as possible?
  • Can text analysis help flag which parts of the story need to be checked?
  • Can we store the results of fact-checking in a way that makes future fact-checking more efficient?
  • How might we make the details of the fact-checking useful to readers without cluttering or distracting?
Sample Milestones
  • (Dependent upon how the Winter project wraps up)
  • Design a clean user-interface for authors and editors to manage checking facts for a story.
  • Build a functioning prototype editor that works like (or is part of) a CMS.
  • Design thinking and ideation about how the fact-check "metadata" could be published or adapted for the audience.
Outcome

The team will make a comprehensive prototype showing how a system like this might work. Based on learning in the class and feedback from our professional network, this has the potential to continue development in Knight Lab with the goal of a product or plug-in which is used in the field.

Students

Laura Barrera

Madeline Kaufman

Tommy Li

2018 Winter
Fluid Factchecking

Important Questions
  • How do writers and editors work through making sure stories are as accurate as possible?
  • Can text analysis help flag which parts of the story need to be checked?
  • Can we store the results of fact-checking in a way that makes future fact-checking more efficient?
  • How might we make the details of the fact-checking useful to readers without cluttering or distracting?
Sample Milestones
  • Design a clean user-interface for authors and editors to manage checking facts for a story.
  • Build a functioning prototype editor that works like (or is part of) a CMS.
  • Design thinking and ideation about how the fact-check "metadata" could be published or adapted for the audience.
Outcome

The team will make a comprehensive prototype showing how a system like this might work. Based on learning in the class and feedback from our professional network, this has the potential to continue development in Knight Lab with the goal of a product or plug-in which is used in the field.