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

arXiv: https://arxiv.org/abs/2109.04152 · HTML: https://mlsanity.com/paper/2109.04152/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 74 references that are in the map.
- First posted on arXiv 9 Sep 2021.

## Builds on (most cited first, 8 of 8)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation](https://mlsanity.com/paper/2004.09813/) (2020)
- [SpanEmo: Casting Multi-label Emotion Classification as Span-prediction](https://mlsanity.com/paper/2101.10038/) (2021)
- [PO-EMO: Conceptualization, Annotation, and Modeling of Aesthetic Emotions in German and English Poetry](https://mlsanity.com/paper/2003.07723/) (2020)
- [A semi-supervised approach to message stance classification](https://mlsanity.com/paper/1902.03097/) (2019)
- [DISCO PAL: Diachronic Spanish Sonnet Corpus with Psychological and Affective Labels](https://mlsanity.com/paper/2007.04626/) (2020)
- [Predicting metrical patterns in Spanish poetry with language models](https://mlsanity.com/paper/2011.09567/) (2020)

## Abstract (arXiv)

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.