Learning to Predict from Crowdsourced Data

Abstract

Crowdsourcing services like Amazon's Mechanical Turk have facilitated and greatly expedited the manual labeling process from a large number of human workers. However, spammers are often unavoidable and the crowdsourced labels can be very noisy. In this paper, we explicitly account for four sources for a noisy crowdsourced label: worker's dedication to the task, his/her expertise, his/her default labeling judgement, and sample difficulty. A novel mixture model is employed for worker annotations, which learns a prediction model directly from samples to labels for efficient out-of-sample testing. Experiments on both simulated and real-world crowdsourced data sets show that the proposed method achieves significant improvements over the state-of-the-art.