Aggregation of pairwise comparisons with reduction of biases
This work addresses the problem of obtaining accurate rankings from biased crowdsourced data for applications like recommendation systems, though it is incremental as it builds on existing aggregation models by adding bias reduction.
The paper tackled the problem of ranking from crowdsourced pairwise comparisons by addressing biases like item position on screens, introducing the factorBT model to reduce these biases and improve ranking accuracy, with empirical studies on real-world datasets showing it outperforms previous models.
We study the problem of ranking from crowdsourced pairwise comparisons. Answers to pairwise tasks are known to be affected by the position of items on the screen, however, previous models for aggregation of pairwise comparisons do not focus on modeling such kind of biases. We introduce a new aggregation model factorBT for pairwise comparisons, which accounts for certain factors of pairwise tasks that are known to be irrelevant to the result of comparisons but may affect workers' answers due to perceptual reasons. By modeling biases that influence workers, factorBT is able to reduce the effect of biased pairwise comparisons on the resulted ranking. Our empirical studies on real-world data sets showed that factorBT produces more accurate ranking from crowdsourced pairwise comparisons than previously established models.