Lexico-semantic and affective modelling of Spanish poetry: A semi-supervised learning approach

TL;DR

This paper introduces a semi-supervised learning method using transformers and lexicon-based features to classify psychological and affective categories in Spanish poetry, specifically sonnets, achieving significant accuracy improvements.

Contribution

It presents a novel semi-supervised approach combining transformers and lexicon features for poetry classification in Spanish, addressing a gap in poetry-focused NLP research.

Findings

Achieved over 0.7 AUC for 76% of psychological categories

Achieved over 0.65 AUC for 60% of affective and lexico-semantic categories

Improved AUC by up to 0.12 over transformer-only models

Abstract

Text classification tasks have improved substantially during the last years by the usage of transformers. However, the majority of researches focus on prose texts, with poetry receiving less attention, specially for Spanish language. In this paper, we propose a semi-supervised learning approach for inferring 21 psychological categories evoked by a corpus of 4572 sonnets, along with 10 affective and lexico-semantic multiclass ones. The subset of poems used for training an evaluation includes 270 sonnets. With our approach, we achieve an AUC beyond 0.7 for 76% of the psychological categories, and an AUC over 0.65 for 60% on the multiclass ones. The sonnets are modelled using transformers, through sentence embeddings, along with lexico-semantic and affective features, obtained by using external lexicons. Consequently, we see that this approach provides an AUC increase of up to 0.12, as opposed to using transformers alone.