Konrad Kording, a neuroscientist at the University of Pennsylvania, was seeking a way to improve conferences and promote attendee interaction. He and his team created ‘Mind Matching’ – a system of machine-learning algorithms that uses natural language processing to match people based on information provided. Mind Matching is now of even greater use when striving to recreate social interactivity in the virtual conference world.

For scientific conferences, the system uses abstracts, as it was found that matching based on keywords does not work as well. The system works by analyzing the text supplied by each person, as well as people they already know and people they hope to meet, and using those analyses to create a matrix of compatibility. Participants can list who they already know in order to ensure meeting new people and can connect with their matches whenever they like. At a recent conference, participants provided three abstracts representative of their research and were matched by an algorithm with up to six other scientists, with whom they had 15-minute conversations.

“These neuromatch conversations were some of the highest quality I’ve had out of any conference, in-person or otherwise. I began to see how good collaborations emerge naturally from great, energetic conversations, if you can find them. Thanks to neuromatch for making that happen.” – Feedback from neuromatch attendee.

The matchmaking method has been expanded to include matchmaking for career hunters and a neuromatch academy, where students will be grouped according to interest. In the future, they plan to improve the matching experience by including additional information from attendees, such as location or time zone.

The code for Mind Matching is available on GitHub.