Cascade of Biased Two-class Classifiers for Multi-class Sentiment Analysis.

In this paper, we describe our participation in the Rest-Mex 2021 Sentiment Analysis Task. Our approach is based on an ensemble of BERT|BETO-based classifiers arranged in a cascade of binary models trained with a bias towards specific classes with the aim of lowering the Mean Average Error. The resulting models were judged in the 2nd and the 3rd place according to the evaluation rule of the Mean Absolute Error.