MIT student uses machine-learning to teach a machine how to compose sonnets.

Machine learning was recently named as the force behind a potential cure for HIV, but now it's a process that is also capable of more artistic endeavours. MIT PhD student J. Nathan Matias used the popular machine-learning Android app Swiftkey in combination with some of Shakespeare's famous words to produce sonnets that rival the master himself.

Swiftkey is an Android input app that uses an algorithm to predict what word you intend to type next, and can be extremely accurate once it understands your patterns and behaviours. Using the app's standard programming, Matias used a dataset of Shakespeare’s words which was incorporated into the algorithm. He also created “Swift-speare,” which provides a touchscreen interface to write poetry.

PSFK provides access to this article and every report, case-study, interview, and analysis that we publish for our members. PSFK Professional Membership also unlocks accessto unlimited customized research assistance and our database of over 100,000 insights on innovation trendspanning across eight industry sectors—from culture and brand to retail and customer experience.
Already a members? Log in