Please note that all workshops have a minimum enrolment. Registrations for workshops which do not run may be transferred or refunded.

Stylometry with R: Computer-Assisted Analysis of Literary Texts

There are currently places remaining on this course (max enrolment: 20)

Instructor: Dr Jan Rybicki (Jagiellonian University, Kraków)

Please note that participants are required to bring their own laptops for this course.

This is a course in stylometry, or the analysis of countable linguistic features of texts. While stylometry has been usually associated with authorship attribution, the same methods are successfully applied to more general text analysis, and, recently, even analysis of other modes such as music and image. The statistics of such features as word, word n-gram or character n-gram frequencies, are not only a highly precise tool for identifying authorship, but can in fact reveal patterns of similarity and difference between various works by one author, works by various authors, finally between authors differing in terms of chronology, gender, genre or narrative styles, between translations of the same author or group of authors, or specific voices such as idiolects of characters in novels. This provides a new opening in literary studies, and the results of a stylometric analysis can be compared and confronted with the findings of traditional stylistics and interpretation. It also opens a new set of questions about style and its transfer, as well as the nature of particular features and language.

The participants of our course will learn major stylometric tools and methods, from simple keywords extraction to machine-learning classification based on text features, followed by visualization techniques ranging from dendrograms to networks. The participants will learn how to identify the problem, define relevant research questions, and design an experiment. We will use our own package written for the R statistical programming environment — ‘stylo’, which allows us to avoid R’s usually steep learning curve – we don’t expect advanced programming skills. We will provide text corpora to use for training purposes, but also hope and expect participant bring their own data and problems to work on.

Topic Modelling in Digital Humanities

There are currently places remaining on this course (max enrolment: 20)

Instructor: Dr Derek Greene (University College Dublin)

Please note that participants are required to bring their own laptops for this course.

Topic models are frequently used in text analysis to uncover the underlying thematic structure of a large corpus, in cases where it is unfeasible to do so manually. A topic modelling algorithm takes a collection of texts as its input, and produces a set of topics, or recurring themes, which repeatedly appear in those texts. The process is exploratory in the sense that the nature and composition of the topics is not known in advance. The outputs of topic modelling can be used to summarise a corpus, to support the development of hypotheses, and to highlight relevant individual texts for further inspection via close reading. Topic models can also help us to identify and study changes in the attention paid to themes or language use over time. As such, topic models are increasingly being used in digital humanities to explore large historical corpora of both fiction and non-fiction texts. This workshop is aimed at providing humanities scholars with an introduction to the key concepts in text analysis, with a particular focus on topic models. We will describe popular methods for topic modelling, and discuss how these methods are used in the context of humanities corpora. Practical issues will also be covered, including data preparation, the application of topic modelling algorithms, and the interpretation of the results of these algorithms.

Indicative Workshop Content:

General introduction to text analysis
Overview of core concepts and methods in topic modelling
Applications of topic modelling in humanities
Preparing your data for topic modelling
Generating topic models from prepared data
Interpreting, evaluating, and visualising the outputs of topic modelling
Further directions for text analysis

Introduction to GIS in the Humanities

There are currently places remaining on this course (max enrolment: 20)

Instructor: Dr Patricia Murrieta-Flores (Lancaster University)

This course will introduce participants to the world of Geographic Information Systems and its use for humanities researchers. Aimed at practitioners with no or a basic understanding of GIS, the course will offer a wide theoretical view of the field of spatial humanities, and will provide some hands on experience with the software.

The course will cover:

a) the state-of-the-art in Geohumanities;
b) the challenges of GIS for humanities research;
c) introduction to GIS and spatial analysis.

Participants won’t need any previous experience with the software, but a good level of digital literacy can be helpful. Participants are encouraged to bring specific datasets they might want to discuss.

DHSI Atlantic

Institiúid Samhraidh do Dhaonnachtaí Digiteacha