Exploring National Library of Scotland datasets with Jupyter Notebooks

Ames, Sarah; Havens, Lucy

doi:10.1177/03400352211065484

Cited by 4 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, HTR can support metadata extraction (Skluzacek et al, 2022), with kws facilitating search against tagged named entities such as place names, dates and individuals [30]. This may allow greater archival sensitivity in metadata extraction and creation, ensuring that resources better represent audiences (Havens, 2020). HTR's wider adoption will not automatically improve an institution's metadata, and we should be mindful of "wishing on" technology to solve social separation without enacting new codes of practice (Seely Brown and Duguid, 2000, pp.…”

Section: Resultsmentioning

confidence: 99%

The implications of handwritten text recognition for accessing the past at scale

Nockels,

Gooding,

Terras

2024

View full text Add to dashboard Cite

PurposeThis paper focuses on image-to-text manuscript processing through Handwritten Text Recognition (HTR), a Machine Learning (ML) approach enabled by Artificial Intelligence (AI). With HTR now achieving high levels of accuracy, we consider its potential impact on our near-future information environment and knowledge of the past.Design/methodology/approachIn undertaking a more constructivist analysis, we identified gaps in the current literature through a Grounded Theory Method (GTM). This guided an iterative process of concept mapping through writing sprints in workshop settings. We identified, explored and confirmed themes through group discussion and a further interrogation of relevant literature, until reaching saturation.FindingsCatalogued as part of our GTM, 120 published texts underpin this paper. We found that HTR facilitates accurate transcription and dataset cleaning, while facilitating access to a variety of historical material. HTR contributes to a virtuous cycle of dataset production and can inform the development of online cataloguing. However, current limitations include dependency on digitisation pipelines, potential archival history omission and entrenchment of bias. We also cite near-future HTR considerations. These include encouraging open access, integrating advanced AI processes and metadata extraction; legal and moral issues surrounding copyright and data ethics; crediting individuals’ transcription contributions and HTR’s environmental costs.Originality/valueOur research produces a set of best practice recommendations for researchers, data providers and memory institutions, surrounding HTR use. This forms an initial, though not comprehensive, blueprint for directing future HTR research. In pursuing this, the narrative that HTR’s speed and efficiency will simply transform scholarship in archives is deconstructed.

show abstract

Section: Resultsmentioning

confidence: 99%

The implications of handwritten text recognition for accessing the past at scale

Nockels,

Gooding,

Terras

2024

View full text Add to dashboard Cite

show abstract

“…10 The GLAM Workbench is a collection of tools and examples using Jupyter Notebooks to explore digital collections provided by GLAM institutions, particularly in Australia and New Zealand (Sherratt, 2021). The NLS has created a Jupyter Notebook project based on the datasets published in their Data Foundry (Ames & Havens, 2022). The Biblioteca Virtual Miguel de Cervantes (BVMC) has published a collection of Jupyter Notebooks that applies a wide range of research methods to different datasets provided by several relevant GLAM institutions (Candela et al, 2022).…”

Section: Related Workmentioning

confidence: 99%

An approach to assess the quality of Jupyter projects published by GLAM institutions

Candela,

Chambers,

Sherratt

2023

Asso for Info Science & Tech

View full text Add to dashboard Cite

GLAM organizations have been digitizing their collections and making them available for the public for several decades. Recent methods for publishing digital collections such as “GLAM Labs” and “Collections as Data” provide guidelines for the application of computational methods to reuse the contents of cultural heritage institutions in innovative and creative ways. Jupyter Notebooks have become a powerful tool to foster use of these collections by digital humanities researchers. Based on previous approaches for quality assessment, which have been adapted for cultural heritage collections, this paper proposes a methodology for assessing the quality of projects based on Jupyter Notebooks published by relevant GLAM institutions. A list of projects based on Jupyter Notebooks using cultural heritage data has been evaluated. Common features and best practices have been identified. A detailed analysis, that can be useful for organizations interested in creating their own Jupyter Notebooks projects, has been provided. Open issues requiring further work and additional avenues for exploration are outlined.

show abstract

The use of artificial intelligence in university libraries in Türkiye: Practices, and perspectives of library directors

Çakmak,

Eroğlu

2024

Information Development

View full text Add to dashboard Cite

Considering the fundamental role of libraries in social integration and information services, adapting service and business processes in parallel with technological advances is a crucial agenda. The impact and use of artificial intelligence technology in processes such as cataloging, content indexing, and responding to user requests have been extensively discussed in the information science literature in recent years. The purpose of this study is to investigate the practices and perspectives of library directors related to the use of artificial intelligence in the services and operations of university libraries in Türkiye. Evaluations related to the impact and use of artificial intelligence applications in the services and operations of university libraries were assessed based on the views of 43 university library directors in Türkiye. The perspectives of library directors reveal that improvements are needed in budget and technical infrastructure, human resources and training, data management, and ethical use to implement AI applications in university libraries in Türkiye.

show abstract

Exploring National Library of Scotland datasets with Jupyter Notebooks

Cited by 4 publications

References 4 publications

The implications of handwritten text recognition for accessing the past at scale

The implications of handwritten text recognition for accessing the past at scale

An approach to assess the quality of Jupyter projects published by GLAM institutions

The use of artificial intelligence in university libraries in Türkiye: Practices, and perspectives of library directors

Contact Info

Product

Resources

About