AI indexing is not a magical quick-fix that will resolve all your metadata needs.  Indeed, it will most likely create new challenges!   So, how do you go about determining your requirements and selecting the indexing services you require?  What happens in practice, once AI Indexing services are in place?  A year in to their AI indexing project, Asharq News will provide an overview of their use of AI within the archive.

Kathey Battrick joined Asharq News in 2019 as a Senior Manager in the Library and Media Management Department. She is responsible for setting up and leading the media library at Asharq, overseeing the management, cataloguing, AI indexing and preservation of the organization’s valuable production assets and archive.

She has a wealth of experience in media and archive management and previously worked as the Director of Operations for ITN Source, the archive and clips sales arm of ITN News in London, where she led projects such as the digitization of ITN’s archive and managed the archive operations team.

Archive data offers a wealth of information that can be used to answer a wide range of questions. For example, to analyse the guest lists of TV programmes to see how the representation of demographic groups changes over time. Or to count the occurrences of locations in wartime newspapers to investigate the geopolitical balance in the reports. This type of quantitative analysis can be performed on a much larger number of archive items than a researcher could reasonably analyse by hand.

AI goes a step further, in not only analysing and aggregating existing data, but learning to create new metadata, and even draw inferences from it. For instance, AI can learn to recognise faces to see who appears in a video, or to classify news articles into categories. A well trained AI can even detect the sentiment expressed in a piece of text.

With these techniques, it may seem that any possible question can be answered. However, there are important limitations. For example, it is easy to search for the term ‘European Union’ in text, but hard to discover how the concept of a union of European countries evolved, when this may have been described in many different ways. It is challenging to distinguish if the sentence ‘That’s a really good idea’ was said sarcastically. Finally, an important question is how representative an analysis of archive material is, given that it is a curated selection.

At Sound and Vision, we are developing support for researchers who aim to answer research questions with quantitative data. In this presentation, we will share our experiences of the questions we can answer, and the ones we can’t, and why. We will also discuss how we are investigating the concept of data stories that combine the traditional qualitative research methods with quantitative analysis to get the best out of both.

Mari Wigham is a data engineer at the Netherlands Institute for Sound and Vision, working on innovative ways of helping researchers to work with the archive. She studied electronic engineering, and has spent her career working in applied research institutes, on projects ranging from virtual avatars to make television accessible to deaf people, to personalised food advice for helping people make healthier choices. Her current work at Sound and Vision combines her experience in the media with her knowledge of semantic technology, to unlock media archives for researchers and provide them with new insights from the data.

—

Rana Klein works as an AI developer at the Netherlands Institute for Sound and Vision. She develops, benchmarks and implements algorithms to enrich archival data. Those enrichments increase the findability of content and open new quantitative opportunities for researchers. Rana graduated from the Master of Logic in 2017. This gave her a fundamental philosophical and mathematical background together with an interdisciplinary mindset.She puts both of these to good use solving real-life problems with artificial intelligence.