Category: text mining

I and my colleagues are very pleased that our project proposal A Text Analytic Approach to Rural and Urban Legal Histories has been funded by the dot.rural Resource Partnership. It is a pilot project that runs for six months, hires two staff part time, and is funded for £53,000. The project is expected to start in the early spring, 2014. Further information is below. Many thanks to my colleagues and the support staff in seeing this proposal through.

• Principal Investigator: Adam Wyner, Department of Computing Science, University of Aberdeen
• Co-Investigator: Jackson Armstrong, School of Divinity, History and Philosophy, University of Aberdeen
• Co-Investigator: Andrew Mackillop, School of Divinity, History and Philosophy, University of Aberdeen
• Associate Investigator: Wim Peters, Department of Computer Science, University of Sheffield
• Partner organisation: Phil Astley, City Archivist, Aberdeen City & Aberdeenshire Archives (ACAA)
• Mentor: George Coghill, Department of Computing Science, University of Aberdeen

Introduction
Aberdeen has the earliest and most complete body of surviving records of any Scottish town, running in near-unbroken sequence from 1398 to the present day. Our central focus is on the ‘provincial town’, especially its articulations and interactions with surrounding rural communities, infrastructure and natural resources. In this multi-disciplinary project, we apply text analytical tools to digitised Aberdeen Burgh Records, which are a UNESCO listed cultural artifact. The meaningful content of the Records is linguistically obscured, so must be interpreted. Moreover, to extract and reuse the content with Semantic Web and linked data technologies, it must be machine readable and richly annotated. To accomplish this, we develop a text analytic tool that specifically relates to the language, content, and structure of the Records. The result is an accessible, flexible, and essential precursor to the development of Semantic Web and linked data applications related to the Records. The applications will exploit the artifact to promote Aberdeen Burgh and Shire cultural tourism, curriculum development, and scholarship.
The scholarly objective of this project is to develop the analytic framework, methods, and resource materials to apply a text analytic tool to annotate and access the content of the Burgh records. Amongst the text analytic issues to address in historical perspective are: the identification and analysis of legal entities, events, and roles; and the analysis of legal argumentation and reasoning. Amongst the legal historical issues are: the political and legal culture and authority in the Burgh and Shire, particularly pertaining to the management and use of natural resources. Having an understanding of these issues and being able to access them using Semantic Web/linked data technologies will then facilitate exploitation in applications.
This project complements a distinct, existing collaboration between the Aberdeen City & Aberdeenshire Archives (ACAA) and the University (Connecting and Projecting Aberdeen’s Burgh Records, jointly led by Andrew Mackillop and Jackson Armstrong) (the RIISS Project), which will both make a contribution to the project (see details on application form). This multi-disciplinary application seeks funding from Dot.Rural chiefly for the time of two specialist researchers: a Research Fellow to interpret the multiple languages, handwriting scripts, archaic conventions, and conceptual categories emerging from these records; and subcontracting the A-I to carry out the text analytic and linked data tasks on a given corpus of previously transcribed council records, taking the RF’s interpretation as input.
 
Resource and Background – Aberdeen Burgh Records
Very few cities in the UK and indeed Northern Europe can rival Aberdeen’s civic archive. Alongside the Scottish Exchequer Rolls and Register of the Great Seal, these volumes are the only near-continuous record that survives for Scotland, running unbroken from 1398 to the present day. Aberdeen’s early Council Registers contain not only records of ‘policy’ but also legal decisions in hundreds of disputes. The Registers include the elections of office bearers, property transfers, regulations of trade and prices, references to crimes and subsequent punishment, matters of public health, credit and debt, cargoes of foreign vessels, tax and rental of burgh lands, woods and fishings, a substantial portion of which relate to rural property. This content means that what may appear as an ostensibly ‘urban’ archive is in fact one of the most important and underexploited ‘rural’ records for medieval and early modern Scotland.
In July 2013 the eight volumes of Aberdeen’s council registers covering the period 1398 to 1509 were recognised by UNESCO as being of outstanding historical importance to the UK.
In 2013 the RIISS proof-of-concept, pilot project is assessing the creation of an online, publicly accessible linked database with samples of the Register’s text with corresponding images. The project involves the transcription and translation of 100 pages from the Register. This corpus of new text generated by the RIISS project will form the basis of material to be used in the Dot.Rural project. The Dot.Rural application is for a new project that will complement the RIISS project.
Rurality and the Law in the Burgh Records
The Aberdeen council registers are records of a primarily legal nature, illuminating the legal history of a community, where the law formalises social conventions, social order, economic priorities, and dispositions and management of resources. From them, we can investigate how such conventions, order, and resources were handled at a time, over time, vertically within social communities, and horizontally across the landscape between Shire and Burgh.
Whereas the technical core of the proposed Dot.Rural project is concerned with applying text analytic tools to the transcribed sample from the 1530s generated by the RIISS pilot, our conceptual interests take a much wider chronological view, spanning the four centuries from c. 1400 to c. 1800. Our central aim is to use Scottish urban records for much more than a study of on the ‘provincial town’ and its interactions with its rural surroundings, which is a topic ripe for investigation. Aberdeen’s records and other historic collections show that the standard demarcation between ‘urban’ and ‘rural’ is inaccurate. Aberdeen served as a social, legal and political interchange for landowners. In an historic period when urban centres were heavily dependent on their rural surroundings, the mental horizons of the civic elite necessarily encompassed the countryside. Within the burgh itself, properties that suggest a liminal or hybrid nature, such as numerous Dee fishings and plots designated simply as ‘the lands beside (the Spital, etc.)’, or ‘a feu … without buildings’ in Footdee, present an environment where the urban and rural were necessarily blended. Our investigations will lead to a deeper understanding of these relationships.
Text Analytic Contribution
Study of these valuable legal historical records has been constrained by access to protected documents and by current research methods. However, there are new, open opportunities to analyse the texts, thereby gaining a deeper understanding of the history and development of communities. Once documents have been digitised, we can apply powerful text analytic tools to the corpus: we annotate the terminology in the documents with a range of semantic, conceptual information; then, we extract or query information from across the documents in complex textual patterns. For example, a query could return all textual passages that contain the semantic concept “person’s name”, followed by several arbitrary intervening words, then followed by the semantic concept “role in some office”, or “property/properties” held in the Shire. In this way, we can then associate people’s names with their roles and their rural/urban personas across the texts. Thus, a range of semantic patterns can be identified that would otherwise be very hard to detect or extract. Such an approach can ground multi-disciplinary investigations of historical societies in large-scale textual sources of information, providing interpretable material on topics such as elites and social practice, relations between social classes and land, urban and rural development, and natural resource management. The text analysis also makes applicable a range of social web-mining approaches on historical text.
Text analysis will help to identify:

• named entities in the Council Registers associated with particular people, places and interests both within the Burgh and the surrounding countryside.
• legal terminology and concepts.
• properties and relationships amongst named entities, including social and political relationships.
• activities of named entities.
• opinions, attitudes, and decisions.

Given these, we can:

• explore the legal and social characterisation of individuals, places, and activities.
• link the register data with maps and auxiliary historical documents.
• facilitate public inquiry into the corpus using queries.

Further Updates
I will post further updates as they become available.
Shortlink here