The current prototype of Art I Don’t Like is designed to be used on a personal computer, with an art set of 52,000 paintings from 18th-20th century European painters. However, it can also be used in museums and gallery spaces. For example, it can be integrated into a welcome kiosk in a museum atrium. The system will be able to recommend pieces of art in the collections that the user might not be familiar with, and then direct them to the location of those pieces. This will create a personalized museum experience for the users who want an opportunity to interact with art and learn about their own art preferences.
This project has two contributions. First, we are developing a new “anti-recommender” system that aims to prevent filter bubbles. Second, we apply recommender technologies to visual art, which can increase the personalization of museum experiences and expose museum patrons to unfamiliar art. We will present this work at conferences focused on the intersection of art and technology, as well as conferences focused on design.