Alexandra Poulovassilis

The COVID-19 pandemic led to the temporary closure of all museums in the UK, closing buildings and suspending all on-site activities. Museum agencies aim at mitigating and managing these impacts on the sector, in a context of chronic data scarcity. “Museums in the Pandemic” is an interdisciplinary project that utilises content scraped from museums’ websites and social media posts to understand how the UK museum sector, currently comprising more than 3,300 museums, has responded and is currently responding to the pandemic. A major part of the project has been the design of computational techniques to provide the project’s museum studies experts with appropriate data and tools for undertaking this research, leveraging web analytics, natural language processing and machine learning. In this methodological contribution, firstly, we developed techniques to retrieve and identify museum official websites and social media accounts (Facebook and Twitter now X). This supported the automated capture of large-scale online data about the entire UK museum sector. Secondly, we harnessed convolutional neural networks to extract activity indicators from unstructured text to detect museum behaviours, including openings, closures, fundraising and staffing. This dynamic dataset is enabling the museum studies experts in the team to study patterns in the online presence of museums before, during, and after the pandemic, according to museum size, governance, accreditation and location. 1

Resource Description Framework datasets can be queried using the SPARQL language but are often irregularly structured and incomplete, which may make precise query formulation hard for users. The SPARQL AR language extends SPARQL 1.1 with two operators—APPROX and RELAX—to allow flexible querying over property paths. These operators encapsulate different dimensions of query flexibility, namely, approximation and generalisation, and they allow users to query complex, heterogeneous knowledge graphs without needing to know precisely how the data is structured. Earlier work has described the syntax, semantics, and complexity of SPARQL AR , has demonstrated its practical feasibility, but has also highlighted the need for improving the speed of query evaluation. In the present article, we focus on the design of two optimisation techniques targeted at speeding up the execution of SPARQL AR queries and on their empirical evaluation on three knowledge graphs: LUBM, DBpedia, and YAGO. We show that applying these optimisations can result in substantial improvements in the execution times of longer-running queries (sometimes by one or more orders of magnitude) without incurring significant performance penalties for fast queries.