English

Re-Assessing the "Classify and Count" Quantification Method

Machine Learning 2021-09-22 v2 Artificial Intelligence Information Retrieval

Abstract

Learning to quantify (a.k.a.\ quantification) is a task concerned with training unbiased estimators of class prevalence via supervised learning. This task originated with the observation that "Classify and Count" (CC), the trivial method of obtaining class prevalence estimates, is often a biased estimator, and thus delivers suboptimal quantification accuracy; following this observation, several methods for learning to quantify have been proposed that have been shown to outperform CC. In this work we contend that previous works have failed to use properly optimised versions of CC. We thus reassess the real merits of CC (and its variants), and argue that, while still inferior to some cutting-edge methods, they deliver near-state-of-the-art accuracy once (a) hyperparameter optimisation is performed, and (b) this optimisation is performed by using a true quantification loss instead of a standard classification-based loss. Experiments on three publicly available binary sentiment classification datasets support these conclusions.

Keywords

Cite

@article{arxiv.2011.02552,
  title  = {Re-Assessing the "Classify and Count" Quantification Method},
  author = {Alejandro Moreo and Fabrizio Sebastiani},
  journal= {arXiv preprint arXiv:2011.02552},
  year   = {2021}
}

Comments

This is the final version of the paper, identical to the one that is going to appear on the Proceedings of the 43rd European Conference on Information Retrieval (ECIR 2021)