DISCO PAL: Diachronic Spanish Sonnet Corpus with Psychological and Affective Labels

Abstract

Nowadays, there are many applications of text mining over corpus from different languages, such as using supervised machine learning in order to predict labels associated to a text using as predictors features derived from the text itself. However, most of these applications are based on texts in prose, with a lack of applications that work with poetry texts. An example of application of text mining in poetry is the usage of features derived from their individual word in order to capture the lexical, sublexical and interlexical meaning, and infer the General Affective Meaning of the text. However, though this proposal has been proved as useful for poetry in some languages, there is a lack of studies for both Spanish poetry and for highly-structured poetic compositions such as sonnets. This article presents a study over a labeled corpus of Spanish sonnets, in order to analyse if it is possible to build features from their individual words in order to predict their General Affective Meaning. The purpose of this is to model sonnets at an affective level. The article also analyses the relationship between the General Affective Meaning of the sonnets and the content itself. For this, we consider the content from a psychological perspective, identifying with tags when a sonnet is related to a specific term (p.e, when the sonnet's content is related to "daydream"). Then, we study how the General Affective Meaning changes according to each of those psychological terms. The corpus used contains 230 Spanish sonnets from authors of different centuries, from 15th to 19th. This corpus was annotated by different domain experts. The experts annotated the poems with affective features, as well as with domain concepts that belong to psychology. Thanks to this, the corpora of sonnets can be used in different applications, such as poetry recommender systems, personality text mining studies of the authors, or the usage of poetry for therapeutic purposes.

LL(O)D and NLP perspectives on semantic change for humanities research

“…To summarise, OntoLex-Lemon offers users a model for representing the relationship between a lexical sense and an ontological entity in linked data. The relationship between lexical and conceptual aspects, or more broadly speaking, linguistic and conceptual aspects of meaning 11 are important for many of the approaches listed in Section 3. This holds for both the knowledge-oriented approaches described in Section 3.1 such as those of Richter, as well as the language-oriented approaches of Section 3.2.…”

“…Digital editions, often modelled in TEI [183], are a rich resource of diachronic language variation. Some corpora, such as the 15th-19th-century Spanish poetry corpus described in [11] contain additional annotations such as psychological and affective labels, but it seems the study was not focused particularly on how these aspects may have changed over time.…”

“…For example, a project that analyses the representation of emotions plays from the 17th to the 19th century, a dataset and lexicon were developed, but these were not explicitly linked to the LL(O)D cloud [107,179]. In contrast to [11], here the labels are explicitly grounded in time. There is a task here for the Semantic Web community to make it easier to publish and maintain LL(O)D datasets for non-Semantic Web experts.…”

“…(a, c) ∈ R&(c, b) ∈ S 10. https://www.w3.org/2016/05/ontolex/#usage11 Note that ontologies are usually described as conceptualisations and of consisting of concepts[68] which makes them an ideal pre-requisite for modelling conceptual shift.…”