Improving User Control and Transparency in the Digital Humanities

Hampson, Cormac; Munnelly, Gary; Bailey, Eoin; Lawless, Séamus; Conlan, Owen

doi:10.1109/culturecomputing.2013.62

Cited by 2 publications

(4 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a study of the update of machine learning in industry, Chiticariu et al [6] noted a gap in the volume of academic research on machine learning, compared with lower levels of uptake within industry and found the causes of this pertained to training data, interpretability and incorporation of domain knowledge. Similarly, the relatively low uptake of machine learning methods in the digital humanities has been attributed to issues pertaining to interpretation and trust [34,13,15]. Imparting domain knowledge into the process of text analysis through interpretation and annotation is also central to humanities research [17,37].…”

Section: Text Mining In the Humanitiesmentioning

confidence: 99%

“…The interpretability of the algorithmic process and the incorporation of domain knowledge are essential to the use of machine learning and text mining in the semantic analysis of literature. The absence of these factors can inhibit adoption of machine learning approaches to text mining in the humanities, due to issues of accuracy and trust in what is often regarded as a 'black-box' process [6,13,15]. This paper presents Curatr, an online platform that incorporates domain expertise and imparts transparency in the use of machine learning for literary analysis.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Curatr: A Platform for Semantic Analysis and Curation of Historical Literary Texts

Leavy

Meaney

Wade

et al. 2019

Metadata and Semantic Research

View full text Add to dashboard Cite

The increasing availability of digital collections of historical and contemporary literature presents a wealth of possibilities for new research in the humanities. The scale and diversity of such collections however, presents particular challenges in identifying and extracting relevant content. This paper presents Curatr, an online platform for the exploration and curation of literature with machine learning-supported semantic search, designed within the context of digital humanities scholarship. The platform provides a text mining workflow that combines neural word embeddings with expert domain knowledge to enable the generation of thematic lexicons, allowing researches to curate relevant sub-corpora from a large corpus of 18th and 19th century digitised texts.

show abstract

Section: Text Mining In the Humanitiesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Curatr: A Platform for Semantic Analysis and Curation of Historical Literary Texts

Leavy

Meaney

Wade

et al. 2019

Metadata and Semantic Research

View full text Add to dashboard Cite

show abstract

“…A comparable situation persists in digital humanities where despite an abundance of research developing automated methods for annotation many projects rely on manual annotation of text (Mahlow et al, 2012). This is due in large part to the domainspecificity of the language of many digital humanities corpora and the high levels of accuracy required to produce reliable analysis (Frank et al;2012, Hampson et al 2013.…”

Section: Automated Annotationmentioning

confidence: 99%

“…Sample paragraphs belonging to each paragraph category were manually selected from the Ryan Report as training data for classifiers. In order to address the issue of the cost of compiling training data in digital humanities projects (Fran et al, 2012;Hampson et al, 2013), minimising the number of examples required was a guiding principle.…”

Section: Training Datamentioning

confidence: 99%

Patterns in language: Text analysis of government reports on the Irish industrial school system with word embedding

Leavy

Keane

Pine

2019

Digital Scholarship in the Humanities

View full text Add to dashboard Cite

Industrial Memories is a digital humanities initiative to supplement close readings of a government report with new distant readings, using text analytics techniques. The Ryan Report (2009), the official report of the Commission to Inquire into Child Abuse (CICA), details the systematic abuse of thousands of children from 1936 to 1999 in residential institutions run by religious orders and funded and overseen by the Irish State. Arguably, the sheer size of the Ryan Report—over 1 million words—warrants a new approach that blends close readings to witness its findings, with distant readings that help surface system-wide findings embedded in the Report. Although CICA has been lauded internationally for its work, many have critiqued the narrative form of the Ryan Report, for obfuscating key findings and providing poor systemic, statistical summaries that are crucial to evaluating the political and cultural context in which the abuse took place (Keenan, 2013, Child Sexual Abuse and the Catholic Church: Gender, Power, and Organizational Culture. Oxford University Press). In this article, we concentrate on describing the distant reading methodology we adopted, using machine learning and text-analytic methods and report on what they surfaced from the Report. The contribution of this work is threefold: (i) it shows how text analytics can be used to surface new patterns, summaries and results that were not apparent via close reading, (ii) it demonstrates how machine learning can be used to annotate text by using word embedding to compile domain-specific semantic lexicons for feature extraction and (iii) it demonstrates how digital humanities methods can be applied to an official state inquiry with social justice impact.

show abstract

Improving User Control and Transparency in the Digital Humanities

Cited by 2 publications

References 1 publication

Curatr: A Platform for Semantic Analysis and Curation of Historical Literary Texts

Curatr: A Platform for Semantic Analysis and Curation of Historical Literary Texts

Patterns in language: Text analysis of government reports on the Irish industrial school system with word embedding

Contact Info

Product

Resources

About