Deep Modeling of Latent Representations for Twitter Profiles on Hate Speech Spreaders Identification Task

Abstract

[EN] In this paper, we describe the system proposed by UO-UPV team for addressing the task Profiling Hate Speech Spreaders on Twitter shared at PAN 2021. The system relies on a modular architecture, combining Deep Learning models with an introduced variant of the Impostor Method (IM). It receives a single profile composed of a fixed quantity of tweets. These posts are encoded as dense feature vectors using a fine-tuned transformer model and later combined to represent the whole profile. For classifying a new profile as hate speech spreader or not, it is compared by a similarity function with the Impostor Method with respect to random sampled prototypical profiles. In the final evaluation phase, our model achieved 74% and 82% of accuracy for English and Spanish languages respectively, ranking our team at 2¿¿ position and giving a starting point for further improvements.