What is FACT?
The Federated-AI for Communication and Trust (FACT) platform is envisioned to be an open, federated AI that will continuously evaluate professional and civic news streams, assign trust rating to content and sources, and progressively adjust their ratings as new and also untold stories are generated and shared.
How does it work?
FACT integrates an assemble of AI models that augment the memory and the “intelligence” of users. It’s a distributed AI platform that federates through self-organization and novel human-AI interaction design
FACT episodic memory engine
- Stores historical facts and sources of news
- Traces news content and degree of distortion over time
- Assigns trust rating
FACT intelligence engine
- Generates narratives based on facts
- Produces counterfactuals and “untold” stories
- Rates trust rating of new articles
The primary audience of FACT are ~ 30 % of the citizens living in the U.S, who are active on the social media. Using textual, chart-based as well as conversational interactive feedback, FACT’s interface can influence end-user interpretations as well news creation, prompting continued action (such as further propagation of fact-based retweets and stories, or writing of news article).
- Literacy about AI and distortion of news content
- Increased trust in news
Civic and Professional Journalists
- Confidence in writing trustworthy stories
- Attention to untold stories
- New models for federated AI combining agent-based modeling, GAN, and human-AI interaction/design
- Behavioral studies/insights
Novel FACT platform distributed AI with novel human-AI interaction design:
- Memory engine (Hebbian learning & agent-based simulation
- Intelligence engine (generative adversarial networks & agent-based modeling)
- Human-AI interaction design
Data and evaluation from controlled experiments with 500+ citizens:
- Lab & field experiments
- Testing effect of FACT for citizens vis-à-vis professional writers
- Impact measures: literacy, perceived trust, confidence, and behavioral change
- ~250 new FACT-based stories
FACT channel reporting to broader audience:
- News produced with FACT by citizen journalists
- Co-authored work with advisory board
(http://www.rcodi.org/)), and an AAAI affiliate. She has been heavily involved with computational social science (agent-based simulation, network dynamics, AI) and social computing, behavioral implications of platforms and algorithmic feedback, “digital nudging”, and large scale experiments. She has involved thousands of citizens in the design & evaluations of digital platforms.
Jia “Jay” is pursuing Computer Science at Purdue University. She is the little kangaroo living in the pocket of Prof. Sabine Brunswicker – the mother kangaroo. Why I say so? She loves to jump in and out of the mother kangaroo’s pocket and explores the outside world but will eventually hop back into her pocket at the end of the day. She has been Prof. Sabine’s student since her undergraduate freshman years and is a soon-to-be PhD student of the mother kangaroo.
Dr. Alok Chaturvedi is a professor in Purdue University’s Krannert School of Management and the Department of Computer Sciences and the Director of the Institute for Social Empowerment through Entrepreneurship and Knowledge (ISEEK) (https://krannert.purdue.edu/centers/iseek/). He has developed and applied AI techniques for over 30 years, intensive experience in large scale modeling and distributed AI , agent-based modeling as well as developed AI for the US government and NATO: e.g. the Synthetic Environment for Analysis and Simulation – Virtual International System (SEAS-VIS), was deployed in Iraq and Afghanistan to test communication strategies (https://goo.gl/ETFuVa).
Rachael Tan was the Communications Manager for RCODI. As an undergraduate Computer Engineering student at Purdue, Rachael is also in organizations such as Society for Asian Scientists and Engineers, the Women in Engineering Program, and Asian dance team Variasian. She has a passion for design and journalism.