An Adaptive Approach of Label Aggregation Using a Belief Function Framework (original) (raw)

Lecture Notes in Business Information Processing, 2017

Abstract

Crowdsourcing knows a large expansion in recent years. It is widely used as a low-cost alternative to guess the true labels of training data in machine learning problems. In fact, crowdsourcing platforms such as Amazon’s Mechanical Turk allow to collect from crowd workers multiple labels aggregated thereafter to infer the true label. As the workers are not always reliable, imperfect labels can occur. In this work, we propose an approach that aggregates labels using the belief function theory besides of adaptively integrating both labelers expertise and question difficulty. Experiments with real data demonstrate that our method provides better aggregation results.

Imen Boukhris hasn't uploaded this paper.

Let Imen know you want this paper to be uploaded.

Ask for this paper to be uploaded.