A creative collaboration. Maintaining and reusing oral history recordings – The National Trust’s Seaton Delaval Hall case study
The Wicked Problem(s)
wp. 001 The eighth property of wicked problems is that: ‘every wicked problem can be considered to be a symptom of another problem.’1 I believe the limited reuse of oral history is, at least in part, a symptom of the insufficient maintenance of access to oral histories. My research into previous attempts to improve the reuse of oral history through digital technology revealed that historically little attention has been given to maintaining oral history archives and repositories.2 However, like the limited reuse of oral histories being a symptom of insufficient maintenance, the scarce maintenance of access to oral histories is also the symptom of other wicked problems. My research focussed primarily on mapping and understanding the various dimensions of the wicked problem of maintaining access to oral histories. Throughout my research I produced several maps and graphics exploring these interlinking wicked problems, editing and adding to them as I learnt more about the reality of maintaining oral history archives and repositories.
Later iteration, The maintenance of oral history – OHD_GRP_0178
wp. 002 The struggle with mapping these wicked problems is how each formulation of the wicked problem of maintaining access to oral history is ‘essentially unique.’3 I had to avoid being too specific with these maps as some factors do not universally apply to all organisations with oral history archives or repositories. This is not uncommon in a design process, as ‘design is fundamentally concerned with the particular.’4 The majority of the outputs I created were specifically tailored to the institutions I was working in as there were several differences. For example, the British Library (established in the 18th century) and the National Trust (founded in the 19th century) have deep-rooted traditions that make adapting to the digital era challenging. In contrast, Archives at NCBS, founded in 2019, emerged in the digital age and is less constrained by analogue custom and practice. The British Library and Archives at NCBS are both archives with oral history collections, while the National Trust is a heritage charity which collects oral histories, but deposits them with the British Library. As a heritage organisation the staff at Seaton Delaval Hall need to manage a wider infrastructure including a cafe, toilets, a garden, a shop, a car park, and a wider voluntary workforce. I recognise all three have space which are open to the public, but unlike at the Hall, the General Manager and the Collections staff at the British Library and Archives at NCBS are not also pointing visitors to the correct parking spots! The Library and the Archives have particular staff to carry out these jobs. In addition, each organisation has different funding streams and staffing structures, all of which will, as I discuss later, contribute to how the access to oral history can be maintained.
wp. 003 Throughout my design process I was adding and taking away from the wicked problem, fluctuating between the specific and the general. Eventually the wicked problem consisted of four general areas of wickedness, which occurred throughout my placements and oral history project: technology, ethics, labour, and money. They are of course not the only areas that contribute to the wicked problem of maintaining access to oral histories as is proven by two similar talks I gave on the wicked problem of oral history access and reuse.5 The one was presented in the summer of 2023 and the other was presented in the spring of 2024. I decided to drop ‘value’ from this graphic because value was something that was very specific to my work with the National Trust, due to their collection policy not including oral histories or any other types of intangible heritage.6
wp. 004 Once I started constructing this portfolio, the areas were reduced once more to the adaptive maintenance required to fulfil public expectations of access, and the barriers to maintenance. Although each situation will differ in their formulation of the wicked problem, I believe these two areas are starting points for thinking about the maintenance of access to oral histories.
From Shelves to Servers
Year
Tech Ethics
Tech
OHT
1981
TAPE system
1983
CD released in Europe and USA
–
–
–
–
1991
Project Jukebox (funded by Apple Library of Tomorrow Grant)
1992
Mini Disc
1993
Copyright Duration Directive (EU)
1994
Web Mail is used in CERN
Steven Spielberg starts the SHOAH institute
1995
1996
WIPO Copyright Treaty
The Internet Archive
1997
Wi-Fi
1998
Digital Millennium Copyright Act (USA) [also had a big effect on the right to repair]
Google
Interclipper demonstration at OHA conference
1999
First SD card
2000
The Dot-com Bubble bursts
VOAHA
2001
Creative commons is founded
2002
Zoom H2 Handy Recorder
2003
2004
Vimeo ; Facebook
Civil Rights Movement in Kentucky Oral History Project
2005
YouTube
2006
Twitter
SHOAH collection moves to the University of Southern California
2007
iPhone ; SoundCloud
Project Jukebox colabs with Testimony Software ; Montreal Life Stories kicks off
2008
FRISCH : First version of OHMS
2009
2010
France enacts the right to be forgotten
Instagram
Crash of VOAHA
2011
Zoom
VOAHA II ; OHMS becomes open source ; Stories Matter is released
2012
2013
Edward Snowden
2014
European Court of Justice legally solidifies the “right to be forgotten” is a human right ; First NFT
wp. 005 Doug Boyd ends his chapter in the book Oral history and Digital Humanities with an anecdote about his daughter coming across a box of cassettes and not recognising the analogue medium. After Boyd explained what the tapes were and how they were used, she simply replied ‘I just want to click on it to listen.’7 This is a useful insight into how developments in technology have affected expectations of access. Where before you had to go to a record shop to buy a CD, cassette, or vinyl; now, nearly all music is available to you via the comfort of your phone. Similarly, in previous decades you had to travel to an archive to access recordings, now oral histories and other archival material are expected to be available online (especially after the Covid-19 pandemic). Digital technologies have created the idea that access to data, information and creative content should be instant, which has also resulted in the structure of oral history repositories moving from shelves to servers.
wp. 006 This move from shelves to servers is a form of adaptive maintenance. Adaptive maintenance is a basic form of maintenance found in software engineering alongside corrective, perfective and preventive maintenance.8 These are mainly used within the field of software engineering, but I have found the idea of adaptive maintenance a helpful term within the context of this wicked problem. Adaptive maintenance means adapting a structure to make it fit an environment which has changed.9 The move from shelves to server within the context of oral history archives and repositories is adaptive maintenance because it is adapting to meet the new public expectation of access – ‘I just want to click on it to listen.’ The most common form of adaptive maintenance is the digitisation of oral histories.
wp. 007 The digitisation of oral history consists of making a digital copy of analogue recordings. My audit of National Trust recordings which had not yet been catalogued by the British Library demonstrated that digitisation is not a one-time activity.10 The audit revealed a wide array of formats including CDs, cassettes, MiniDiscs, and an unknown digital file type, which might have to be converted in order to be accessed. Sadly, the large digitisation project at the British Library, Unlocking our Sound History or UOSH,had just finished,11 and so much of the resources needed to digitise were no longer easily available.
Screenrecording of C1168 Audit 2023 (non-catalogued items) – OHD_COL_0262
wp. 008 Alongside the digitisation of analogue recordings and associated data, adaptive maintenance within oral history archives and repositories, as I have previously discussed, involves moving from shelves to servers. The entire structure surrounding the material, the catalogue, and the storage location, must become digital, leaving carbon paper and index cards behind. Rob Perks writes about how he experienced this during his time at National Life Stories, the oral history charity that is situated within the British Library. He notes a ‘painful and protracted’ move from analogue to digital at the British Library, including the acquisition of a digital management system, the development of a new accessioning system, and the training required to ensure staff gained sufficient skills and knowledge to implement the new digital content correctly.12
wp. 009 Adaptive maintenance does not remove the existence of analogue material or systems. Digitisation rarely replaces analogue systems completely and the rate of adoption will differ radically between institutions and organisations. This can be referred to as the ‘digital divide.’ In the early 2000s, the digital divide primarily referred to the access to hardware, software, and the internet. More recently it has been extended to encompass people’s digital skills, so their ability to use technology, the frequency they use it, and how much it is integrated into their lives.13
Collection of photographs of the National Trust Collections’ forms – OHD_COL_0272
Collection of photographs of The British Library – OHD_COL_0271
wp. 010 This uneven adoption of digital systems often leads to hybrid systems, consisting of analogue and digital components, as I saw in the office of National Life Stories.14 Nor does this adaptive maintenance eradicate issues experienced with analogue material such as ‘folios [that have] fallen behind books stack.’15 This follows a basic rule of invention and development: ‘To invent the sailing ship or steamer is to invent the shipwreck.’16 Therefore, after digitisation archivists have to deal with dropped analogue folios and the digital equivalent – dead links.17
Audit of NLHF oral history projects – OHD_COL_0278
wp. 011 In addition to dead links during my research period there were also multiple IT incidents at the National Trust,18 a cyber-attack at The British Library,19 websites that were not working,20 and technology that became obsolete.21
wp. 012 This is not an argument against the move from shelves to servers, after all my cat also weed on my paper PhD archive, causing me to throw some archival material away.22 This was not a great loss though, because I had already digitised the material. I offer these examples of breakdowns to highlight the perils of any structure, digital or analogue, and how these need to be considered equally. Digital technology is not magic but simply another form of a structure and all structures need maintenance.
wp. 013 The change in society’s expectation of access (‘I just want to click on it to listen’) has led to a mass transformation of the oral history structures into hybrid systems with new additional forms of maintenance labour. In addition, we also need to consider how this change in expectations has not only influenced the systems which create access, but also the feelings we have around access. As Almut Leh writes, ‘the digital representation of original documents has considerably promoted their dissemination and thus their visibility.’ This results in them being more easily accessible and capable of being ingested and interpreted by machines on a mass scale.23 Outside of oral history, this increase in access has had significant consequences on the ethics, laws, and guidelines which surround data management, which in turn have affected how oral histories can be accessed.
wp. 014 However, these laws were not explicitly made for oral histories and so how they should be applied can be confusing. Those who maintain the access to oral histories now also need to rethink how they classify and handle material. Through my research, specifically my work during the placements, I identified three areas which have been affected by the changing expectations of access: ownership, personal information, and sensitive content.
Ownership
Screenrecording of C1168 Audit 2023 (copyright) – OHD_COL_0262
wp. 015 The ownership of oral history and materials in general has changed a lot over the decades as the internet has made sharing and duplicating material a lot easier. My copyright audit of the National Trust’s sound collection illustrated the history of oral history and copyright.24
wp. 016 Currently, in the UK and most of the West an oral history is understood as a recorded performance, and therefore the performer, i.e. those speaking on the recording hold copyright over their voices. Those recorded must sign their copyright over to the relevant party. In most cases, this will be the archive or repository holding the oral history, if a recording is to be reused. Importantly, this rule of copyright applies to every recorded oral history, even those recorded before this law was enacted. This is why I created the foundations for the Trust to develop a workflow that could be used to obtain copyright or to confirm that the oral history is an orphan work.25
Orphan Work
wp. 017 A work is considered ‘orphaned’ when the original creator is not contactable or not known. In the case of oral history, a recording becomes an orphan work when the speaker was born 120 years ago (some organisations, like the British Library, the cut-off point is 100 years instead of 120.) In some cases, however, it might be preferable to try to contact the next of kin in cases where third parties are mentioned in the recording.
wp. 018 The collection of personal information has become increasingly controversial with the rise of social media. The Facebook-Cambridge Analytica data scandal in 2016 became a particular poignant example of large companies using their customers’ personal data as if it was their own asset.26 Since the 2010s, laws have been created to protect people’s personal information, with the classic example being the EU’s General Data Protection Regulation (GDPR), which became effective in May 2018, replacing the Data Protection Directive of 1995. The GDPR was later adopted by the UK after its formal exit from the EU in 2020. Many data protection laws around the world have either been modelled on the GDPR, or the EU’s Data Protection Directive. While some data protection laws, like India’s Digital Personal Data Protection Act, apply only to digital data, the GDPR covers all data, including oral history.
wp. 019 Oral histories generally collect two forms of personal data: the personal information of the interviewee on the permission forms, and the recording of the interview. The former is easy to handle under the GDPR because what data is collected is clearly understood as personal data: name, address, contact information etc. When I was designing the Research Room at Seaton Delaval Hall, all the forms I designed had to follow the same GDPR guidelines.
wp. 020 The management of the interview recording is slightly more complicated. Data protection laws like the GDPR were designed to protect people’s privacy, but oral history is recorded for public knowledge. This means oral history is personal information for public consumption, which does not fit GDPR’s framework. This causes some confusion under archivists and those with similar professions.
wp. 021 Data protection never occupied a central position in my placements, but it was always present. I researched it while I developed the Research Room for Seaton Delaval Hall and the takedown policy for Archives at NCBS. The general advice I started giving people when asked about data protection, was to adopt a continuous awareness of the legislation around data. This is admittedly very basic, but I believe it captures the general aim of the regulation:
Make sure the data is kept in a safe place and access to this storage is monitored and recorded.
Make sure to be transparent with the owner of the data, in terms of where it will be stored and who will use it.
And make sure it’s easy for them to ask questions about their data and have it removed if necessary.
wp. 022 In terms of designing and developing outputs, GDPR and other data protection regulations made me consider how a system which holds and grants access to personal data must be transparent and open, and above all easy to understand and navigate by both the owner of the personal data and the person holding it. This was particularly vital when I designed the processes and forms for the Research Room at Seaton Delaval Hall.27
Sensitive Content
wp. 023 The third area of ethics is the management of sensitive content. This is not particularly linked to the rise of the internet, as moral outrage and the management of morally dubious or harmful content predates the digital world. However, the ease of, and scale of, access through the internet has led to public concerns that focus on children or vulnerable adults discovering upsetting, inappropriate or ‘triggering’ material. It has therefore become common to conduct regular sensitivity checks on archival material in response to shifting moral and ethical standards.
wp. 024 The sensitivity check I made for Archives at NCBS was specifically designed to be quick. Archives at NCBS generally follow the archival principle of ‘More Product, Less Process’ outlined by Mark Greene and Dennis Meissner: so speed was key.28 I therefore created a green light/red light system which could quickly categorise material as sensitive or not. There were two perspectives on sensitivity: material which could harm the donor, their kin, or close associates, and material which could harm the researcher accessing the material. For the former I created a flowchart and for the latter I simply had a list of sensitive and non-sensitive material.
The part of my Miro board of NCBS placement relating to the sensitivity check – OHD_WHB_0246
The two versions of the "Sensitivity Check Workflow" document contain both similarities and key differences. Below is a comparison:
### Common Elements: 1. **Purpose and Definitions**: - Both documents emphasize that the sensitivity check is designed to identify sensitive material in archival collections. - Definitions of sensitive and non-sensitive material are present in both versions, including red and green label guidelines.
2. **Examples of Sensitive and Non-Sensitive Content**: - Both versions classify sensitive material under categories like personal information, medical records, slander, and cultural sensitivity. - Non-sensitive materials include public information, certain academic records, and older data (30+ years).
3. **Cultural Sensitivity**: - Both documents stress the importance of contextualizing culturally insensitive materials.
---
### Key Differences: 1. **Version Naming**: - **V1 (February 16, 2023)** is simpler and less structured than **V2 (February 28, 2023)**.
2. **Flowchart in V2**: - V2 introduces a **flowchart** to guide decisions on sensitivity labeling, making the process more visual and systematic. V1 lacks this tool.
3. **Additional Context in V2**: - V2 provides more detail on the steps for contextualizing material during sensitivity checks, including advisories and catalog descriptions for sensitive items.
4. **Expanded Categories in V2**: - V2 introduces a **second part** to the sensitivity check, focusing on content that could harm visitors (e.g., offensive or triggering materials). - New examples of sensitive materials in V2 include **explicit sexual content**, **graphic violence**, and more nuanced rules for cultural insensitivity.
5. **Inclusion of Misinformation in V2**: - V2 explicitly mentions misinformation and provides guidelines for its contextualization, while V1 does not address this.
6. **Terminology and Philosophy**: - V2 describes the sensitivity check as "prescriptive" and distinct from the Archive's broader philosophy on access and sensitive material handling. - It emphasizes providing advisories and detailed catalog descriptions, even for embargoed material.
---
### Recommendations: - **Flowchart Addition**: V2's flowchart provides a clear decision-making aid and could be helpful if added to earlier workflows. - **Misinformation Context**: Including misinformation handling, as in V2, could enhance sensitivity processes. - **Part Two Sensitivity Checks**: V2 expands the scope to visitor safety, which could be valuable for archives focused on inclusivity. - **Consistency**: If you prefer the concise nature of V1, consider integrating V2's updates selectively to avoid complexity.
wp. 025 The purpose of this quick sensitivity check was to get material available quickly and then later do more thorough sensitivity checks. This approach differed significantly from that of the staff at Seaton Delaval Hall, who took a more deliberate approach to managing the sensitivity of their oral histories. They decided to create a group of staff members that would work together as a form of ethics board.29 This again shows the wicked problem of maintaining access to oral histories will vary between cultures and institutions, and therefore require different approaches.
wp. 026 Out of the three areas I have discussed, sensitivity is the most nebulous and dynamic, as it is mostly dictated by social opinions rather than any rules or regulations, although laws such as the Online Safety bill in the UK might change this.30 Nevertheless, all three areas of ethics might look very different in the future. This is why such documents and processes, like a takedown policy, are important. A takedown policy exists exactly because things change. The takedown policy I made for Archives at NCBS emphasises change and underlines the importance of taking things on a case-by-case basis.31
ChatGPT Comparison of OHD_RPT_0249 - Archives at NCBS Takedown policy [generated 06 / 01 / 2025]
Here are the key differences between the three versions of the "Archives at NCBS Takedown Policy" documents:
---
### **1. Focus and Scope**: - **Version 1 (V1)**: - Primarily describes the "Notice and Takedown" policy for handling complaints about online material. - Focuses on specific scenarios like copyright, personal data, defamation, or errors in publishing. - Emphasizes removal, negotiation, and possible outcomes (removal, replacement, or unchanged return).
- **Version 2 (V2)**: - Adds historical context about "Notice and Takedown" policies and their evolution, referencing laws like the DMCA and "Right to Be Forgotten." - Discusses more detailed review processes for different complaint types, including copyright, personal data, and culturally sensitive material. - Introduces the concept of negotiating balances between public access and individual rights, recommending a panel review for complaints.
- **Version 3 (V3)**: - Expands the policy to include alterations, such as metadata edits, and internal staff requests for redaction or changes. - Formalizes a structured, multi-stage process: "Request and Receipt," "Review and Report," "Negotiate and Amend," and "Agree and Action." - Addresses internal accountability and archiving of all change requests and resolutions.
---
### **2. Detail and Complexity**: - **V1** is simpler and focuses on immediate actions for handling takedown requests. - **V2** introduces detailed sections on different complaint types (e.g., copyright, defamation) and historical/legal background. - **V3** includes more granular procedural steps and additional types of requests (e.g., metadata changes, internal staff flags).
---
### **3. Handling of Specific Cases**: - **V1**: - Describes removing material online temporarily during review and emphasizes swift resolutions. - No mention of internal requests or metadata changes.
- **V2**: - Begins discussing ethical considerations (e.g., historical preservation vs. privacy). - Suggests negotiating outcomes but does not formalize a multi-step resolution framework.
- **V3**: - Introduces new solutions like redactions, Google search removals, and partial removal. - Outlines separate approaches for different requesters (e.g., associated individuals, staff, concerned citizens). - Encourages thorough documentation and archiving of the resolution process for transparency.
---
### **4. Tone and Guiding Principles**: - **V1** has a reactive tone, focusing on removing material until issues are resolved. - **V2** balances proactive and reactive measures, embedding ethical and historical considerations. - **V3** adopts a proactive, systematic, and inclusive tone, emphasizing negotiation, transparency, and detailed procedural guidance.
---
### **5. Structural Changes**: - **V3** introduces a more formalized four-stage process: - Receipt of requests, - Review and generation of a report, - Negotiation (if applicable), - Final action and documentation.
- **V2** only outlines the need for case-by-case handling without explicitly structuring the process.
---
### Summary: - **V1** is a straightforward guide to takedown complaints. - **V2** expands scope, adding historical context, and ethical considerations. - **V3** evolves into a comprehensive "Takedown and Alterations" policy, emphasizing procedural rigor, inclusivity, and accountability.
Let me know if you'd like more detailed comparisons or additional analysis!
wp. 027 Things will change. Even during the four years of my project, technology has dramatically changed. In November 2020 I wrote a blog post about a computer being able to write my PhD by ingesting the archive I was creating.32 Two years later I could test this proposition with ChatGPT. I even experimented with it summarising interviews.33 AI has also complicated copyright and data protection with many of the large tech companies developing AI being accused of scraping material from the internet without asking permission of the creators. As a result, the tech companies are facing several class action lawsuits and the outcome of the lawsuits could again affect how we share information.34 However, at the time of writing, many of the archives have already been scraped to be used in large datasets for training large language models.
Newspaper cutout “Facebook teaches AI to ‘forget’ data’ – OHD_SCP_0008
Code
Creation Date
Title
Contents Summary
Tags
Location(s)
OHD_WRT_0241
20221216
ChatGPT test
Me testing if an AI chat bot could write my PhD. It could not.
wp. 027 Every formulation of a wicked problem is unique, even if the topic is the same. Each version of the wicked problem of maintaining access to oral history will differ in the type of adaptive maintenance that is required: digitising material, acquiring copyright, updating the catalogue, sensitivity checking. What hinders the completion of this adaptive maintenance will also differ, causing the access to oral histories to fail as a result of dead links or incomplete paperwork. However, there are recurring barriers – the usual suspects – which appear across versions of this wicked problem, obstructing the completion of maintenance (adaptive or corrective): lack of flexibility, and limited resources.
Lack of Flexibility
Google Gemini Summary of OHD_WRT_0135 - The Journey of Oral History Technologies [generated 06 / 01 / 2025]
This text explores the challenges of developing and implementing digital oral history technologies, drawing parallels to the inaccurate predictions of future technologies in popular culture (like Back to the Future Part II).
Key Arguments:
Early Optimism and Subsequent Challenges: Early projects like Project Jukebox demonstrated initial optimism about the potential of technology to revolutionize oral history. However, these projects often faced unforeseen challenges, including:
- Technological Limitations: Rapid technological advancements quickly rendered early solutions obsolete, requiring constant maintenance and updates. - Funding Constraints: Limited resources often hindered the development and maintenance of sophisticated technologies. - Design Flaws: Overemphasis on aesthetics or specific user groups can lead to exclusion and limited usability.
The Importance of Human Factors: The text emphasizes the importance of human factors, such as:
- Digital Divide: Acknowledging and addressing the digital divide in terms of access, skills, and usage. - User-Centered Design: Considering the diverse needs and preferences of different user groups, including oral historians, archivists, and the general public. - Ethical Considerations: Addressing issues of data privacy, digital inequality, and the environmental impact of digital technologies.
The Need for a More Human-Centered Approach: The text argues for a more human-centered approach to digital archives, emphasizing the importance of:
- Collaboration and Communication: Fostering effective communication and collaboration between oral historians, archivists, technologists, and community members. - Learning from Past Failures: Analyzing past projects to identify and address recurring challenges. - Embracing a "DIY" Approach: Exploring more pragmatic and sustainable solutions that leverage existing tools and skills.
Overall:
The text provides a critical analysis of the challenges and opportunities presented by digital technologies in the context of oral history archiving. It emphasizes the need for a nuanced and collaborative approach that acknowledges the limitations of technology and prioritizes human needs and values.
Google Gemini Summary of OHD_WRT_0172 - Chpt. 01 History of oral history tech [generated 06 / 01 / 2025]
This chapter explores the attempts to find a technological solution to the problem of archived oral history recordings. It discusses the challenges faced by oral historians and sound archivists in preserving oral histories and the failures of past technological solutions like TAPE, Project Jukebox, VOAHA, Interclipper, and Stories Matters. The chapter also analyses the reasons for these failures, including a focus on aesthetics over functionality, a lack of consideration for long-term preservation, and a reliance on new technologies that are not always sustainable.
Here are the key points from the chapter:
Oral historians and sound archivists have different needs for technology. Oral historians want technology that helps them focus on the orality of recordings and contextualize them, while sound archivists prioritize long-term preservation.
Many past attempts at creating oral history technology have failed because they did not address the needs of both groups. For example, they focused on creating beautiful interfaces that were difficult to maintain or used technologies that became obsolete.
There is a need for a more sustainable approach to oral history technology that considers both functionality and long-term preservation.
The chapter concludes by calling for a more DIY approach to oral history technology, using established technologies and focusing on creating solutions that are easy to maintain and will last over time.
wp. 028 I interviewed the archivist who built the archive at the contemporary art gallery BALTIC in Gateshead when it first opened in the early 2000s.36 He talked me through the various iterations of the online archive and the processes behind them. It is a story I became increasingly familiar with throughout my research.
Interview with BALTIC archivist – SDH_AI_001
wp. 029 Like the former archivist at BALTIC, when oral historians first started to develop technologies to improve the access to oral histories at the end of the twentieth century and the start of the twenty-first, there was no software that could do what the oral historians wanted it to do, so they made their own.37 However, the oral historians had not anticipated how their technologies would fail and, as a result, neglected their maintenance, ultimately leading to their demise. Like many others, oral historians then began looking beyond their field, outsourcing solutions and purchasing off-the-shelf materials.
wp. 030 More recently the consequences of outsourcing were sadly demonstrated by the cyber-attack on The British Library. In a blog post Simon Bowie, who had previously worked at the British Library, writes how the Library’s management were not replacing IT staff when they left, and were instead increasingly outsourcing parts of the IT systems.38 This led to the Library’s IT maintenance team being overstretched, leaving the system vulnerable to attacks.39
wp. 031 In addition to the inflexibility of digital structures, specifically outsourced ones, I also witness an inflexibility in process and policies. This was most stark with the National Trust, who do not include oral history or any other form of intangible heritage in their collection policy.40 How this is restrictive when adaptive maintenance is needed and how I created outputs which tried to make adaptive maintenance easier can be seen in the Case Example section of this portfolio.
Limited Resources
wp. 032 Maintenance is work so it requires time and money. These are however in short supply.
Between indulging in delicious food and gandering around the stunning campus of the National Centre of Biological Sciences (NCBS), I sit at a hot desk in the basement where the Archives at NCBS is housed. The term ‘basement’ is slightly misleading as the sun shines through windows which face a sunken outdoor amphitheatre, where I can watch paradise birds flirt with each other in the trees. When not distracted by birds or food, my attention might be drawn away from my work by one of the eleven other people working in the Archive. It is the loudest archive I have ever been in, even when I discount the constant humming of the air conditioning. It is also the most welcoming workplace I have ever worked in. The Archives at NCBS is a hub of multidisciplinary folk, all coming together to build this archive, which is still very much in its infancy, celebrating its fourth birthday on this month. Therefore, a lot of the work is focused on growing the archive, with some team members creating a digital catalogue, others expanding the collection, and many involved in developing the various work flows necessary to keep an archive running.'
Notebook notes for the away-day activities – OHD_NTB_0316
wp. 033 Archives at NCBS is in a completely different position than the other organisations I worked with, because it is so young – only five years at the time of writing. As I wrote in a blog post in my first month there, ‘a lot of the work is focussed on growing the archive, with some team members creating a digital catalogue, others expanding the collection, and many involved in developing the various workflows necessary to keep an archive running.’41 Although I spent most of my time at Archives at NCBS developing their takedown policy and their sensitivity checks, I also observed the work environment and practices. I was asked to facilitate their annual staff away-day, which provided an opportunity to understand the Archives’ work culture. The larger questions to be explored during the away-day were:
What is the collection policy?
Are we going to be a resource centre?
Are we going to be a consultancy centre?
(The team structure)
wp. 034 During the day the staff brainstormed around the four activities of the archive: collect, educate, research, and engage. The final outcome of this activity, that I observed, demonstrates how much happens in a space like Archives at NCBS.42 However, within these different sections there is even more work done, as seen in the workflow I created, which maps out the process of collecting and then making something publicly accessible.43 Yet, there is work absent from this workflow as it notably does not show the maintenance tasks that need to occur when a deposit is finally made in the archive.
wp. 035 I used the framework Mierle Laderman Ukeles offers in her Manifesto for Maintenance Art, 1969! to help articulate how there are two systems that operate under the roof of Archives at NCBS.44 The maintenance system within the Archives is the public archive, and the development system is the knowledge hub.
First half of the graphic ‘What is Archives at NCBS?’ – OHD_GRP_0261
wp. 036 My solutions to how these two systems might be handled was partially based on the final activity of the away-day, which was an exercise where the staff had to write what they would like to stop, start, and continue in the workplace.45 Additional ideas came from my experience of working at Seaton Delaval Hall, because I noticed similarities in the respective work environments. The Hall, like Archives at NCBS, is a functioning heritage site and so there are other activities to do besides managing the collection and acquiring new material. Both also have a similar number of staff, so it felt appropriate to bring duplicate activities across the organisations, including updates of individual activities during the weekly meeting.
Second half of the graphic ‘What is Archives at NCBS?’ – OHD_GRP_0261
wp. 036 My experience at Archives at NCBS and my other placements revealed how much work is needed to keep these heritage and public history organisations operational. Fitting all the activities that make up this work into one workday is not an easy feat. So, if an activity is not valued or does not contribute as a funding output, then it is easier to sideline the task in favour of something more profitable.
Chasing funding
We went to three different heritage sites of varying status and every single one of them mentioned funding many, many, many times.
wp. 037 Every archive, heritage or other public history organisation will have different funding sources. In the UK, the largest funding body is the National Lottery Heritage Fund (NLHF). The former BALTIC archivist who I interviewed mentioned they had had to wait for funding before they could update their system, which eventually came from NLHF.46 Seaton Delaval Hall received funding from the NLHF for The Curtain Rises project, which contained a collaboration with Northumbria University called Rising Stars.47
wp. 038 The NLHF prefers particular types of projects, as reflected in their grant guidelines and funding decisions.48 In a screen recording I used during a talk, I searched the NLHF website for projects that were undertaking ‘development,’ ‘restoration,’ or ‘maintenance.’49 The search revealed a focus on development and restoration, the latter of which is only necessary when maintenance fails. In How Buildings Learn Stewart Brand quotes John Ruskin, ‘Take proper care of your monuments, and you will not need to restore them. […] Watch an old building with an anxious care; guard as best you may, and at any cost, from every influence of dilapidation.’50
wp. 039 Similarly, when I made a casual audit of oral history projects funded by the NLHF, there was little to no evidence of the recordings being archived, suggesting energy and money was put towards recording over maintenance.51
wp. 040 There are cases of maintenance activity being funded, but this is often limited to digitisation. The British Library received funding for Unlocking our Sound Heritage, which was also partially funded by the NLHF.52 Archives at NCBS received a grant for Arcadia, a family charitable foundation, ‘to collect, preserve and make available online endangered cultural artefacts.’53 Digitisation is a rare measurable form of maintenance. Maintenance is primarily invisible as I discussed – ‘The Unseen: Maintenance Labour on Heritage Sites.’54
Google Gemini Summary of OHD_PRS_0120 - The Unseen: Maintenance Labour on Heritage Sites [generated 06 / 01 / 2025]
Key Arguments:
The Invisibility of Maintenance: Maintenance work is often invisible and undervalued, taken for granted until things go wrong.
The Impact of This Invisibility: - Underfunding: Maintenance projects receive less funding than development or restoration projects, as they lack the "wow factor" and are seen as less impactful. - Exploitation of Volunteer Labor: The undervaluation of maintenance work leads to the increased reliance on unpaid volunteers, potentially displacing paid professionals. - Unsustainable Practices: A focus on development and restoration can lead to unsustainable practices that require constant and costly interventions.
The Importance of a Maintenance Perspective: Recognizing the crucial role of maintenance in ensuring the long-term sustainability of heritage sites. Designing and implementing solutions that are adaptable, maintainable, and integrate seamlessly into existing maintenance routines.
Implications for the Author's PhD Research: Acknowledging the realities of maintenance work at Seaton Delaval Hall, including resource constraints and the role of volunteers. Designing a solution that is adaptable and easy to maintain by the Hall's staff. Collaborating closely with Hall staff to understand their needs and integrate the project into their existing workflows.
Key Concepts:
Maintenance as Invisible Labor: The work of maintaining a heritage site is often invisible and undervalued, taken for granted until things break down.
The Development vs. Maintenance Dichotomy: Society tends to prioritize development and restoration over maintenance, leading to underfunding and underappreciation of maintenance work.
The Importance of Sustainability: Designing solutions that are sustainable in the long term requires careful consideration of maintenance needs, including resource constraints and the availability of skilled labor.
wp. 041 The invisibility of maintenance, or inability to be quantified, makes it an undervalued activity in capitalist society. Meaning:
“mundane housekeeping and clerical work is too uncool” is what the powers that be tell us. They use interns not for a fresh set of eyes, but because it’s the kind of work that’s considered low labour.
– Response to my feedback form for the document ‘What is Archives at NCBS?’ – OHD_FRM_0325
wp. 042 The wicked problem of maintaining access to oral histories could arguably be solved if adaptive maintenance were consistently carried out as expectations of access change. However, this rarely happens due to rigid systems and limited resources. Both these obstacles are the product of not considering or accommodating maintenance labour. My work with the National Trust and Seaton Delaval Hall avoided this by focussing on how my work and outputs would be maintained beyond the completion of my research project.
Horst Rittel, and Melvin Webber, ‘Dilemmas in a General Theory of Planning,’ Policy Sciences 4, no. 2 (1973): 165. ↩︎
For more on this see section The Practice, and for an even more in depth look see ‘Oral History and Technical Failures’ in the Critical Commentary. ↩︎
Richard Buchanan, ‘Wicked Problems in Design Thinking,’ Design issues 8, no. 2 (1992), 17. ↩︎
James Louwerse, H., Jun 23, 2023, Reusing oral history in GLAM: a wicked problem. OHD_Archive. OHD_PRS_0265; James Louwerse, H., Apr 25, 2024, Iraq Symposium talk. OHD_Archive. OHD_PRS_0300. ↩︎
National Trust, National Collections Development Policy 2019-2024, 2019. Read more about this in the section The National Trust. ↩︎
Douglas A. Boyd, ‘”I Just Want to Click on It to Listen”: Oral History Archives, Orality, and Usability,’ in Oral History and Digital Humanities, ed. Douglas A. Boyd and Mary A. Larson, (Palgrave Macmillan, 2014), 77. ↩︎
E. Burton Swanson, ‘The Dimensions of Maintenance,’ in Proceedings of the 2nd international conference on Software engineering, ed. Raymond T. Yeh and C. V. Ramamoorthy, (IEEE Computer Society Press, 1976), 494. ↩︎
Robert B. Perks, ‘Messiah with the microphone? Oral historians, technology, and sound archives,’ in The Oxford Handbook of Oral History, ed. Donald A. Ritchie, (Oxford University Press, 2011), 326. ↩︎
Jan A. G. M. Van Dijk, ‘Digital divide: Impact of access,’ in The International Encyclopedia of Media Effects, ed. Patrick Rössler, Cynthia A. Hoffner, and Liesbet van Zoonen Rössler, (John Wiley & Sons, 2017), 1-11. ↩︎
James Louwerse, H., May 23, 2023, Collection of photographs of The British Library. OHD_Archive. OHD_COL_0271. ↩︎
James Louwerse, H., Mar 31, 2021, Zoom comment on digital archives. OHD_Archive. OHD_SSH_0146. ↩︎
Paul Virilio, The Original Accident, (Polity, 2007), 10. ↩︎
Almut Leh, ‘”The answer is 42” – When Algorithms Take over Digital Memory. Experiences with Artificial Intelligence in the Archive Deutsches Gedächtnis,’ in Von Menschen und Maschinen: Mensch-Maschine-Interaktionen in digitalen Kulturen, ed. V. Selin Gerlek, Sarah Kissler, Thorben Mämecke, Dennis Möbus, (Hagen University Press, 2022), 173. ↩︎
James Louwerse, H., Sep 6, 2023, NT BL Report. OHD_Archive. OHD_RPT_0274. ↩︎
James Louwerse, H., Jun 21, 2023, NT property recommendations for PhD placement. OHD_Archive. OHD_RPT_0263. ↩︎
See my work on Seaton Delaval Hall’s Research Room in the portfolio section, Seaton Delaval Hall. ↩︎
Mark Greene, and Dennis Meissner, ‘More product, less process: Revamping traditional archival processing,’ The American Archivist 68, no. 2, (2005): 208-263. ↩︎
James Louwerse, H., Aug 5, 2024, SDH oral history strategy. OHD_Archive. OHD_RPT_0296. ↩︎
Alex Danchev and Mierle Laderman Ukeles, “Maintenance Art Manifesto,” in 100 Artists’ Manifestos, ed. Alex Danchev (Penguin Group, 2011), 382. ↩︎
James Louwerse, H., 2021, Recording with BALTIC archivist. SDH_PP. SDH_AI_001. ↩︎
James Louwerse, H., Oct 4, 2024, Timeline of technologies. OHD_Archive. OHD_SPS_0310. ↩︎
The Sound and Moving Image catalogue was powered by SirsiDynix, a company in the United States which produces integrated library system software and associated services for libraries. I can currently not prove this because the British Library’s Sound and Moving Image catalogue is down, since the cyber-attack. ↩︎
