The Novel in the Spanish Silver Age : : a Digital Analysis of Genre Using Machine Learning / / José Calvo Tello.

• VerfasserIn: Tello, José Calvo,
• Place / Publishing House: Bielefeld : : Bielefeld University Press,, 2021.
• Year of Publication: 2021
• Language: English
• Physical Description: 1 online resource (471 pages)

What distinguishes an adventure novel from a historical novel? Can the same text belong to several genres? More to one than to another? Have some existing genres been overlooked? To answer these and similar questions, José Calvo Tello combines methods from Linguistics (lexicography), Literary Studies (genre theory), and Computer Science (machine learning, natural language processing). Located in the interdisciplinary field of Digital Humanities, this study analyzes a newly developed corpus of 358 Spanish novels of the silver age (1880-1939), which includes authors like Baroja, Pardo Bazán, or Valle-Inclán. Calvo Tello's key result is a graph-based model of literarygenre that reconciles recent theoretical approaches.

Table of Contents

Cover -- Contents -- Acknowledgements -- 1. Introduction -- 2. Previous Research and Theoretical Framework -- 2.1 Silver Age: Genre, Novel, and Subgenre of the Novel -- 2.1.1 Introduction -- 2.1.2 Edad de Plata: Silver Age -- 2.1.3 Literary Genre and Novel in this Period -- 2.1.4 The Novel and its Borders -- 2.1.5 Realist and Naturalist Novel -- 2.1.6 Historical and Adventure Novels -- 2.1.7 Comedy Novels -- 2.1.8 Erotic Novels -- 2.1.9 Social Novels -- 2.1.10 One-Author-Labels: Nivola, Greguería, and Episodio Nacional 2.2 Genre in Digital Humanities: Methods, Features, and Data Representation -- 2.2.1 Introduction -- 2.2.2 Genre in Computer Science -- 2.2.3 Genre in Digital Humanities -- 2.2.4 The Start of Genre Classification -- 2.2.5 Literary Genre in the Past Years -- 2.2.6 Conclusions and General Patterns -- 2.3 Theory of Genre -- 2.3.1 Basic Distinctions about Concepts and Definitions -- 2.3.2 Models of Genres -- 2.3.3 Macro-Models of Genres -- 2.3.4 Perspectives on Genres -- 2.3.5 Conclusions -- 3. Data: Texts and Metadata -- 3.1 Corpus of Novels of the Spanish Silver Age: CoNSSA and CoNSSA-canon 3.1.1 Introduction -- 3.1.2 Literary Corpora -- 3.1.3 Statistical Population of Authors -- 3.1.4 Statistical Population of Prose -- 3.1.5 Statistical Population of Novels -- 3.1.6 Definition of the Corpora: CoNSSA and CoNSSA-canon -- 3.1.7 Criteria for Selection -- 3.1.8 Digitization Steps -- 3.1.9 Description of the Corpus -- 3.1.10 Gender Distribution -- 3.1.11 Publication of Data -- 3.2 Metadata -- 3.2.1 Introduction -- 3.2.2 Metadata, Distant Reading, and Hypotheses Testing -- 3.2.3 Typology of Metadata -- 3.2.4 Editorial and Administrative Metadata -- 3.2.5 Descriptive Metadata 3.2.6 Author's Metadata -- 3.2.7 Text and Genre Metadata -- 3.2.8 Place and Period of the Action -- 3.2.9 Protagonist Metadata -- 3.2.10 Other Literary Metadata -- 3.2.11 Description of the Metadata of CoNSSA -- 3.3 Filtering the Corpus through Classification: Are all Texts in CoNSSA Novels? -- 3.3.1 Introduction -- 3.3.2 Corpus CORDE: Bag of Words and Metadata -- 3.3.3 CORDE 1860-1960 + CoNSSA -- 3.3.4 Binary Class Evaluation of Parameters -- 3.3.5 Multi-Class Evaluation of Parameters -- 3.3.6 Binary Prediction of Genre of Disputed Texts 3.3.7 Multi-Class Prediction of Genre of Disputed Texts -- 3.3.8 Conclusions and Modification of the Corpus -- 4. Feature Engineering: Linguistic Annotation and Transformation -- 4.1 Grammatical, Lexical, Semantic, and Textual Annotation -- 4.1.1 Introduction -- 4.1.2 Format of Annotation -- 4.1.3 Vocabulary and Punctuation -- 4.1.4 Grammatical Annotation -- 4.1.5 Entities -- 4.1.6 Semantic Annotation -- 4.1.7 Pragmatic and Textual Annotation -- 4.2 Transformations of Lexical Data and Linguistic Annotation -- 4.2.1 Introduction -- 4.2.2 Classic Transformation of Frequency of Features.