Search results

This 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.

In 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.

Catalogued 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.

Our 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.

This study investigates Rokkan's research programme in the light of the differences between case- and variables-based methodologies. Three phases of the research process are distinguished. Studying the way Rokkan actually proceeded in the research within his Europe project, we find that he follows the protocols of case-methodologies such as grounded theory. In the second phase of the research process, however, he constructs variables-based models as tools for his macro-historical comparisons. To get to variables from the sensitizing concepts coded in the first phase, Rokkan defines his variables as close to cases as possible: variables as nominal level typologies, types as variable values. He thus faces two interrelated dilemmas. First, a philosophy of science dissonance: he legitimates his research only with reference to a variable-methodology, while his research is thoroughly case based. Second, a paradox of double coding: using variable-based models in the second phase, the status of the knowledge available in the first phase memos is degraded. Rokkan cannot decide between the two main solutions to these dilemmas: The first solution is to discard his heterogeneous data, instead working only with homogeneous data that opens up to more consistently variables-oriented research. The second solution is to replace the notion of variables/variable values with typology/types, thereby returning to cases, pursuing comparative case reconstructions in the third phase of research. The study concludes in favour of the second solution.