Abstract. The sensitivity review of government records is essential before they can be released to the official government archives, to prevent sensitive information (such as personal information, or that which is prejudicial to international relations) from being released. As records are typically reviewed and released after a period of decades, sensitivity review practices are still based on paper records. The transition to digital records brings new challenges, e.g. increased volume of digital records, making current practices impractical to use. In this paper, we describe our current work towards developing a sensitivity review classifier that can identify and prioritise potentially sensitive digital records for review. Using a test collection built from government records with real sensitivities identified by government assessors, we show that considering the entities present in each record can markedly improve upon a text classification baseline.

No abstract

This article explores how current methods and approaches in archives are under serious challenge because of the changes brought about by the move to the digital. The availability of digital records has meant that new needs and new possibilities have opened up for users, including new ways of reading. The nature of archives themselves are changing-they are moving from being collections of individual texts to be pored over to data to be made sense of. New tools and techniques have emerged and are available now which offer radical new possibilities for research, but these bring new challenges about trust and the sheer volume of records to be handled. The traditional approaches of applying metadata to facilitate the finding of relevant material and of regarding digital documents as something like electronic paper is no long viable. What is needed is a new approach in which archivists and scholarly researchers see archives as collections of data which are capable of analysis by a range of sophisticated tools and which are capable of being interpreted in a range of different ways.

Este trabajo explora la forma en que los actuales métodos y enfoques archivísticos están seriamente cuestionados por los desafíos que provoca la transformación digital. La disponibilidad de los documentos digitales ha supuesto que a los usuarios se le planteen nuevas necesidades y se abran nuevas posibilidades, incluidos los nuevos modos de consultar. La naturaleza de los mismos archivos está cambiando –están pasando de ser colecciones de textos individuales a ser datosminuciosamente estudiados para darles sentido. Han aparecido nuevas herramientas y técnicas que ya están disponibles y que ofrecen nuevas y radicales posibilidades para la investigación, pero esto comporta nuevos retos en cuanto a la confianza y al gran volumen de documentos a tratar. Los enfoques tradicionales que atribuyen metadatos para facilitar la búsqueda del material relevante y la consideración de los documentos digitales como algo similar al papel electrónico no son viables. Lo que se necesita es una nueva aproximación en la que los archiveros y los investigadores vean los archivos como colecciones de datos que son susceptibles de análisis usando toda una gama de sofisticadas herramientas y que son capaces de ser interpretados con toda una gama de fórmulas diferentes. This article explores how current methods and approaches in archives are under serious challenge because of the changes brought about by the move to the digital. The availability of digital records hasmeant that new needs and new possibilities have opened up for users, including new ways of reading. The nature of archives themselves are changing—they are moving from being collections of individual texts to be pored over to data to be made sense of. New tools and techniques have emerged and are available now which offer radical new possibilities for research, but these bring new challenges about trust and the sheer volume of records to be handled. The traditional approaches of applying metadata to facilitate the finding of relevant material and of regarding digital documents as something like electronic paper is no long viable. What is needed is a new approach in which archivists and scholarly researchers see archives as collections of data which are capable of analysis by a range of sophisticated tools and which are capable of being interpreted in a range of different ways.

No abstract