Enabling Complex Analysis of Large-Scale Digital Collections: Humanities Research, High Performance Computing, and transforming access to British Library Digital Collections

1. Overview

The drive in the Gallery, Library, Archive, and Museum (GLAM) sector towards opening up collections data, ⁵ as well as the growth in data published by publicly-funded research projects, means humanities researchers have a wealth of large-scale digital collections available to them (Lui, 2015, Terras 2015). Many of these datasets are released under open licences that permit uninhibited use by anyone with an internet collection and modest storage capacity. A few humanities researchers have exploited these resources, and their interpretations make claims that change our understanding of cultural phenomena (for example, see Schmidt, 2014; Smith et al., 2015; Cordell et al., 2013; Huber, 2007; Leetaru, 2015). Nevertheless, there remain major barriers to the widespread uptake of these data sets, and related computational approaches, by humanities researchers, which risks diminishing the relevance of the humanities in “big data” analysis (Wynne, 2015). These barriers include:

• fragmentation of communities, resources, and tools;
• lack of interoperability;
• lack of technical skills: “mainstream researchers in the humanities and social sciences often don’t know what the new possibilities are” (ibid) and seldom have the technical experience to experiment (Hughes, 2009; Mahony and Pierazzo, 2012).

A common response to this lack of awareness and computational skills is to build web-based interfaces to data ⁶ or federated services and infrastructures ⁷. Whilst these interfaces play a positive role in introducing humanities researchers to large-scale digital collections, they rarely fulfil the complex needs of humanities research which constantly questions received approaches and results, or allow researchers to tailor analysis without being limited by shared assumptions and methods (Wynne, 2013).

2. Method

We explored the challenges associated with deploying and working with large-scale digital collections suitable for humanities research, using a public domain digital collection provided by the British Library ⁸. This 60,000 book dataset covers publication from the 17th, 18th, and 19th centuries, or – seen as data – 224GB of compressed ALTO XML that includes both content (captured using an OCR process) and the location of that content on a page. Using UCL's centrally funded computing facilities ⁹ we worked from March-July 2015 with RITS and a cohort of four humanities researchers (from doctoral candidates to mid-career scholars) to ask queries that could not be satisfied by search and discovery orientated graphical user interfaces. Working in collaboration we turned their research questions into computational queries, explored ways in which the returned data could be visualised, and captured their thoughts on the process through semi-structured interviews.

3. Results

We successfully ran queries across the dataset tracking linguistic change, identifying core phrases, plotting and understanding the placing of illustrations, and mapping locations mentioned within core texts. We found that building queries that generate derived datasets from large-scale digital collections (small enough to be worked on locally with familiar tools) is an effective means of empowering non-computationally trained humanities researchers to develop the skill-sets required to undertake complex analysis of humanities data. ¹⁰

Figure 1: A search for mentions of various infectious diseases (Cholera, Whooping Cough, Consumption, and Measles) across the 60,000 book dataset. We compared the profound spikes for Cholera in the dataset with known data regarding epidemics in the UK (Chadwick, 1842; Wall, 1893) which appear as the bars on the graph, showing a relationship between the first major UK outbreak of Cholera and its appearance within the written record of the time. There are further pronounced spikes 1870s and 1880s: these are not associated with UK epidemics, but there were outbreaks in the US and elsewhere. Identifying the texts that refer to these outbreaks allows us to look more closely at these clusters and to understand the relationship between public health, epidemiology, and the published historical record.

From a technical perspective, this pilot highlighted various sticking points when using infrastructure developed predominantly for scientific research. 224GB is only moderately large by comparison to the scientific datasets UCL RITS usually encounters, but although there are shared assumptions between research infrastructures (adoption of technical standards, and the sharing of tools, approaches and research outputs (Wynne, 2015)) most of the UK’s university eScience ¹¹ infrastructure has been constructed specifically to run scientific and engineering simulations, not for search and analysis of heterogeneous datasets. Our task here had a large textual input, a simple calculation, and a small output summary. By comparison, the typical engineering simulation addresses moderately sized numerical input data, runs a long, complicated calculation, and produces a large output. Poor uptake in the arts and humanities (Atkins et al., 2010; Voss, 2010) has meant that these resources have not been optimised for these workloads. The file system and network configuration of Legion – UCL RITS's centrally funded resource for running complex and large computational scientific queries across a large number of cores – did not match the way that the dataset in question was structured (a large number of small zipped XML files).

The complexities associated with redeploying architectures designed to work with scientific data (massive yet very structured) to the processing of humanities data (not massive but more unstructured) should not be understated, and are a major finding of this project. Relevant libraries (such as an efficient XML processor) needed to be installed and optimised for the hardware. Also, the data needed to be transformed to a structure that the parallel file system (Lustre) could address efficiently (that is, fewer, larger files).

Best practice recommendations for comparable projects emerged from this work: the need to build multiple derived datasets (counts of books and words per year, words and pages per book, etc) to normalise results and maintain statistical validity; the necessity of documenting decisions taken when processing data and metadata; and the value of having fixed, definable data for researchers to explain results in relation to (and in turn, the risks associated with iterating datasets). Pointers to how to process the derived datasets were welcomed, but it was at this stage that the researchers were confident to “go it alone” without our support. We also discovered that a core set of four or five queries gave most of the humanities researchers the type of information they required to take a subset of data away to process effectively themselves: for example, keywords in context traced over time; NOT searches for a word or phrase that ignored another word or phrase, etc. As Higher Education Institution (HEI)-based subject librarians regularly handle routine research queries, we contend that training librarians to aid humanities researchers in carrying out defined computational queries via adjustable recipes would improve access to infrastructure, and cut down on the human-resource intensive nature of this approach. In turn, research computing programmers could be invoked as collaborators for their expertise, such as for developing more complex searches beyond the basic recipes.

4. Conclusion

We successfully mounted large-scale humanities data on high performance computing University infrastructure in an interdisciplinary project that required input from many professionals to aid the humanities scholars in their research tasks. The collaborative approach we undertook in this project is labour intensive and does not scale. Nevertheless, we found many research questions can be expressed with similar computational queries, albeit with parameters adjusted to suit. We recommend, therefore, that HEIs or HEI clusters looking to build capacity for enabling complex analysis of large-scale digital collections by their non-computationally trained humanities research should consider the following activities:

• Invest in research software engineer capacity to deploy and maintain openly licensed large-scale digital collections from across the GLAM sector in order to facilitate research in the arts, humanities and social and historical sciences,
• Invest in training library staff to run these initial queries in collaboration with humanities faculty, to support work with subsets of data that are produced, and to document and manage resulting code and derived data.

Our pilot project demonstrates that there are at present too many technical hurdles for most individuals in the arts and humanities to consider analysing large-scale open data sets. Those hurdles can be removed with initial help in ingest and deployment of the data, and the provision of specific, structured, training and support which will allow humanities researchers to get to a subset of useful data they can comfortably and more simply process themselves, without the need for extensive support.