CLS INFRA D5.1. Review of the Data Landscape

This is a revew of the present-day data lanscape prepared as deliverable 5.1. in the framework of the Horizon2020 Project "Computational Literary Studies Infrastracture". This landscape review, for which Work Package 5 is responsible, focuses on intellectual access, i.e. providing guidance for finding and sharing literary data, while Work Package 6 approaches the task from a more technological side, collecting and analyzing literary corpora, available formats, tools, and metadata in order to create an exploratory catalogue / inventory of literary corpora and to provide a transformation matrix/toolbox for solving common issues. Yet we coordinate our efforts – beginning with the compilation of the table of literary collections – therefore one can regard these as two sides of the same coin. The review’s point of departure is the abundance of existing data and their diversity or heterogeneity as regards corpus design and underlying concepts, for example the definitions of text (is it a source, an edition, a data set? see chapter 3), the purpose of a corpus (e.g. general, reference, or monitoring corpora, special purpose corpora; see chapter 4), central considerations or criteria regarding the construction of a corpus (sampling, balancing, representativeness, annotation model(s), data format(s); see likewise chapter 4). How can I go about obtaining data without transgressing ethical or legal boundaries (see chapter 5)?

We ask: How can we assist literary scholars in searching for and finding existing data that are relevant to their own research questions? And additionally, what kind of research question is relevant concerning the present-day state of the data landscape and literariness and textuality?

The review contains following sections:

1. Introduction: Enhancing Data Findability and Accessibility……………………..……..4

2. Reference Case Studies Highlighting Research Context and Corpus Design

(Haiku, Slovak Novel)…………………………………………………………………………..7

3. Research Context: Impact of the Digital Paradigm on Literary Text Collections….…..9  

3.1. “Literary” (Return of Essentialism, Poetics, and Classifications)……………………..12

3.2. “Text” (between Bag of Words and Ordered Hierarchy of Content Objects)………..15

3.3. Modelling vs. Exploratory Approaches to Textual Data……………………………….18

3.4. Use Case: Collecting the Haiku………………………………………………………….20 

4. Corpus Design: Methods of Selection and Sampling (Use Case: the Slovak Novel)….23

4.1. Typology of Corpora According to Their Purpose……………………………………..25

4.1.1. General-Purpose Collections……………………………………………………….....26

4.1.2. Reference Corpora (Subcorpora of)………………………………………………….28

4.1.3. Digital Critical Editions………………………………………………………………….29

4.1.4. Monitor Corpora…………………………………………………………………………30

4.1.5. Corpora Compiled on the Basis of a Research Question…………………………..31

4.1.6. Opportunistic Corpora………………………………………………………………….31

4.2. Key Considerations for Selection and Sampling (Relative to Different Types of Corpora, e.g. Exploratory or Modelling)…………………………………………...…………32

4.2.1. Corpus Architecture / Composition (Size, Eligibility, Structuring of Texts and Annotations, Entity Typing)……………………………………………………………………34

4.2.2. Completeness…………………………………………………………………………..36

4.2.3. Representativeness…………………….………………………………………………37

4.2.4. Proportion (Balance)……………………………………………………………………38

4.2.5. Frequent Biases………………………………………………………………………...39

4.3. Data Formats………………………………………………………………………………41

4.4. Metadata’s Formats and Structures (Generic vs. Domain-Specific Repositories)….42

4.5. Access to Corpus Data: Retrieval Tools (GUI, APIs, OAI-PMH)…………………….45

5. Legal and Ethical Considerations………………………………………………………….46

6. Outlook……………………………………………………………………………………….51