Matching and Grokking: Approaches to Personalized Crowdsourcing

Abstract

Personalization in computing helps tailor content to a person’s individual tastes. As a result, the tasks that benefit from personalization are inherently subjective. Many of the most robust approaches to personalization rely on large sets of other people’s preferences. However, existing preference data is not always available. In these cases we propose leveraging online crowds to provide on-demand personalization. We introduce and evaluate two methods for personalized crowdsourcing: taste-matching for finding crowd workers that are similar to a personalization target, and taste-grokking, where crowd workers explicitly predict the requester’s tastes. Both approaches show improvement over a non-personalized baseline, and have various benefits and drawbacks that are discussed.