Crowdsourced Task Routing via Matrix Factorization
This work addresses the challenge of improving accuracy in crowdsourced systems by enabling better worker selection, though it is incremental as it applies existing collaborative filtering techniques to a specific domain.
The paper tackles the problem of predicting crowd workers' accuracy on new tasks to optimize task routing, showing that matrix factorization methods, particularly probabilistic MF, outperform baselines in reducing prediction error and identifying the best workers across various data scales and similarity conditions.
We describe methods to predict a crowd worker's accuracy on new tasks based on his accuracy on past tasks. Such prediction provides a foundation for identifying the best workers to route work to in order to maximize accuracy on the new task. Our key insight is to model similarity of past tasks to the target task such that past task accuracies can be optimally integrated to predict target task accuracy. We describe two matrix factorization (MF) approaches from collaborative filtering which not only exploit such task similarity, but are known to be robust to sparse data. Experiments on synthetic and real-world datasets provide feasibility assessment and comparative evaluation of MF approaches vs. two baseline methods. Across a range of data scales and task similarity conditions, we evaluate: 1) prediction error over all workers; and 2) how well each method predicts the best workers to use for each task. Results show the benefit of task routing over random assignment, the strength of probabilistic MF over baseline methods, and the robustness of methods under different conditions.