Conversational Fact Checking

The goal would be to provide factual verification of the news that supports further questions about the context (history, alternative points of view, evidence, etc.) of a news story and/or quote. The challenge would be to provide immediate access to the facts in real or semi-real time.

It is demonstrably the case that once false information is encountered, it is difficult to remove from people’s mindset. Even if the information is corrected with later correct information, it is difficult to extinguish.

If false information is corrected in the moment however, there is a greater chance that it will be corrected in the mind of the reader/viewer.

We would like to propose an approach to this that integrates fact checking with ongoing broadcast news reports. In particular, we would like to look at how a user could, in the midst of watching a news show, could ask questions with regard to the content being presented. Starting with the simple question “is this true?” and moving to more complex questions about different points of view “What does Bernie Sanders think of this?” we want to build out a conversational interface to the news.

The goal would be to provide factual verification of the news as it is presented that supports further questions about the context (history, alternative points of view, evidence, etc.) of a news story and/or quote. The challenge would be to provide immediate access to the facts in real or semi-real time.

Our focus this quarter is the development of a capabilities platform that defines the tools that we can use to develop an entire range of products. In service of this, we will use fact checking as the first application with the goal of developing a broader system that allows for conversational interaction with information systems that use the content and context of what you are watching as the topic of the conversation.

TECHNICAL APPROACH:

  • Access closed captioning
  • Integrate with one of the voice-based assistant platforms
  • Provide feedback in either speech or on the screen

Presentation Slides

Results

Results from the project

  • How to translate live-spoken human words into computer "truth"

    Our Knight Lab team spent three months in Winter 2018 exploring how to combine various technologies to capture, interpret, and fact check live broadcasts from television news stations, using Amazon’s Alexa personal assistant device as a low-friction way to initiate the process. The ultimate goal was to build an Alexa skill that could be its own form of live, automated fact-checking: cross-referencing a statement from a politician or otherwise newsworthy figure against previously fact-checked statements...

    Continue Reading

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.

Students

Carlos Belardi

Joe Blackman

David Caine

Martin Johnson

Andrew Lapin

Jennifer Liu