Quality of Descriptive Information on Cultural Heritage Objects: Definition and Empirical Evaluation

Effective data processing depends on the quality of the underlying data. However, quality issues such as inconsistencies and uncertainties, can significantly impede the processing and subsequent use of data. Despite the centrality of data quality to a wide range of computational tasks, there is currently no broadly accepted, domain-independent consensus on the definition of data quality. Existing frameworks primarily define data quality in ways that are tailored to specific domains, data types, or contexts of use. Although quality assessment frameworks exist for specific domains, such as electronic health record data and linked data, corresponding approaches for descriptive information about cultural heritage objects remain underdeveloped. Moreover, existing quality definitions are often theoretical in nature and lack empirical validation based on real-world data problems. In this paper, we address these limitations by first defining a set of quality dimensions specifically designed to capture the characteristics of descriptive information about cultural heritage objects. Our definition is based on an in-depth analysis of existing dimensions and is illustrated through domain-specific examples. We then evaluate the practical applicability of our proposed quality definition using a curated set of real-world data quality problems from the cultural heritage domain. This empirical evaluation substantiates our definition of data quality, resulting in a comprehensive definition of data quality in this domain.

Behind the Scenes of a New Display

Today we opened our new foyer display — and if you’re passing by, we warmly invite you to stop for a moment and take a look. Exhibitions like this are a wonderful way to share highlights from the U…

Signal Messenger Group

Follow this link to join a group on Signal Messenger.

Digital Library Systems Developer · University of Glasgow

Job PurposeThe Digital Library Team within Information Services at the University of Glasgow supports digital access to globally significant research collect...

Out of Context! Managing the Limitations of Context Windows in ChatGPT-4o Text Analyses

In recent years, large language model (LLM) applications have surged in popularity, and academia has followed suit. Researchers frequently seek to automate text annotation - often a tedious task – and, to some extent, text analysis. Notably, popular LLMs such as ChatGPT have been studied as both research assistants and analysis tools, revealing several concerns regarding transparency and the nature of AI-generated content. This study assesses ChatGPT’s usability and reliability for text analysis – specifically keyword extraction and topic classification – within an “out-of-the-box” zero-shot or few-shot context, emphasizing how the size of the context window and varied text types influence the resulting analyses. Our findings indicate that text type and the order in which texts are presented both significantly affect ChatGPT’s analysis. At the same time, context-building tends to be less problematic when analyzing similar texts. However, lengthy texts and documents pose serious challenges: once the context window is exceeded, “hallucinated” results often emerge. While some of these issues stem from the core functioning of LLMs, some can be mitigated through transparent research planning.

ai4lam - Fantastic Futures 2024 Papers