Finding light in dark archives: using AI to connect context and content in email

Abstract

Email archives are important historical resources, but access to such data poses a unique archival challenge and many born-digital collections remain dark, while questions of how they should be effectively made available remain. This paper contributes to the growing interest in preserving access to email by addressing the needs of users, in readiness for when such collections become more widely available. We argue that for the content of email to be meaningfully accessed, the context of email must form part of this access. In exploring this idea, we focus on discovery within large, multi-custodian archives of organisational email, where emails’ network features are particularly apparent. We introduce our prototype search tool, which uses AI-based methods to support user-driven exploration of email. Specifically, we integrate two distinct AI models that generate systematically different types of results, one based upon simple, phrase-matching and the other upon more complex, BERT embeddings. Together, these provide a new pathway to contextual discovery that accounts for the diversity of future archival users, their interests and level of experience.

Human resource management in the age of generative artificial intelligence: Perspectives and research directions on ChatGPT

“…What is clear is that technology by itself does not disrupt business and society, but that only does so in conjunction with efficiency gains, setting of new standards and business model innovation (Cortada, 2006(Cortada, , 2013. And as the history of dot-com boom and bust has shown, understanding how to commercially exploit a technology can be more difficult than mastering it (Decker et al, 2022).…”

Enhancing Customer Service in Shopping Malls with an Advanced Chatbot-Integrated Concierge Device

“…Reading customer emails and understanding their needs can be time-consuming, particularly when the email has to be manually forwarded to the appropriate person if sent to the wrong department (Decker et al, 2022). AI can significantly reduce response times by scanning and labeling emails and offering automated suggestions, references, and solutions to draft effective responses.…”

EMCODIST: A Context-based Search Tool for Email Archives

“…In practice, it can be difficult to find answers to these questions with existing search modalities, and in our project, we sought to develop a discovery tool that seeks to find some possible ways for users to find better information for their queries. We propose the prototype tool called EMCODIST, to allow users a context-rich search of organizational email corpora 4 [9]. The EMCODIST focuses on e-discovery to extract chains of emails beyond keyword search and facilitates a context-based search of user queries across multiple custodians, which is particularly relevant to organisational email collections.…”