Editorial

Paul Puschmann, Joana Maria Pujadas-Mora, Eva van der Heijden — Tue, 06 Feb 2024 00:00:00 +0100

In this new editorial of Historical Life Course Studies key shifts are discussed. We welcome Joana Maria Pujadas-Mora as new co-editor in chief and Eva van der Heijden as associate editor. We thank Luciana Quaranta for her contributions to the development of the journal. Over the past years, Historical Life Course Studies has experienced substantial growth in terms of output and impact. The journal got indexed in Scopus and an application for admission to the Web of Science is pending. Social media engagement and upcoming video releases further enhance the journal's outreach. Gratitude extends to sponsors for Diamond Open Access support, as well as to all authors, reviewers, and readers who jointly contribute to the success of Historical Life Course Studies. The editors look with confidence to the future and hope to welcome many submissions over the next years.

More Efficient Manual Review of Automatically Transcribed Tabular Data

Thu, 04 Apr 2024 00:00:00 +0200

Any machine learning method for transcribing historical text requires manual verification and correction, which is often time-consuming and expensive. Our aim is to make it more efficient. Previously, we developed a machine learning model to transcribe 2.3 million handwritten occupation codes from the Norwegian 1950 census. Here, we manually review the 90,000 codes (3%) for which our model had the lowest confidence scores. We allocated these codes to human reviewers, who used our custom annotation tool to review them. The reviewers agreed with the model's labels 31.9% of the time. They corrected 62.8% of the labels, and 5.1% of the images were uncertain or assigned invalid labels. 9,000 images were reviewed by multiple reviewers, resulting in an agreement of 86.4% and a disagreement of 9%. The results suggest that one reviewer per image is sufficient. We recommend that reviewers indicate any uncertainty about the label they assign to an image by adding a flag to their label. Our interviews show that the reviewers performed internal quality control and found our custom tool to be useful and easy to operate. We provide guidelines for efficient and accurate transcription of historical text by combining machine learning and manual review. We have open-sourced our custom annotation tool and made the reviewed images open access.