Human Interaction News Trust System
Fake news is a problem across a variety of platforms with detrimental impacts. HINTS is a passive network indicator that detects fake news by analyzing the pattern of how it is shared and by whom. The type of news that people have liked in the past is a good predictor of news they will like in the future. HINTS is initialized by seeding it with labeled data, such as content labeled as untrustworthy and accounts that have liked or shared untrustworthy content. Our algorithm then predicts which content will be labeled as fake news later on. Fake news is not a problem in a vacuum. It becomes a problem proportional to visibility. Focusing on people likely to propagate fake news and URLs likely to be fake allows for remediation before the damage is done.
Natalie Lao is the leader of the team and provides business, management, and policy. She has worked as a PM at Apple, Google, and the MIT Internet Policy Research Initiative.
Dr. Elan Pavlov is an MIT alumnus and an inventor with experience in 3 startups and author of 10+ patents, including the current patent pending for the HINTS algorithm.
Andrew Tsai is a Masters student in computer science at MIT. He has experience working in big data, machine learning, and inference. In the past, he has worked at eBay and IBM.
Keertan Kini is an MIT alumnus who has worked at Google, Microsoft, Akamai, Barefoot Networks, etc. He has experience with distributed systems, cloud computing, and big data.