[Paper Review] AI in Archival Science -- A Systematic Review

G. N. Shinde, Tiana Kirstein+2 more|arXiv (Cornell University)|Oct 7, 2024

Anomaly Detection Techniques and Applications4 citations

TL;DR

This systematic review investigates the integration of artificial intelligence (AI) in archival science, analyzing current AI techniques used to address challenges in records management, appraisal, retention, and data retrieval. The study identifies key AI-driven strategies that enhance efficiency and transparency in archival workflows, advocating for interdisciplinary collaboration between AI and archival science to advance digital preservation and information organization.

ABSTRACT

The rapid expansion of records creates significant challenges in management, including retention and disposition, appraisal, and organization. Our study underscores the benefits of integrating artificial intelligence (AI) within the broad realm of archival science. In this work, we start by performing a thorough analysis to understand the current use of AI in this area and identify the techniques employed to address challenges. Subsequently, we document the results of our review according to specific criteria. Our findings highlight key AI driven strategies that promise to streamline record-keeping processes and enhance data retrieval efficiency. We also demonstrate our review process to ensure transparency regarding our methodology. Furthermore, this review not only outlines the current state of AI in archival science and records management but also lays the groundwork for integrating new techniques to transform archival practices. Our research emphasizes the necessity for enhanced collaboration between the disciplines of artificial intelligence and archival science.

Motivation & Objective

• To analyze the current state of AI integration in archival science and records management.
• To identify specific AI techniques employed in addressing archival challenges such as retention, appraisal, and organization.
• To evaluate the effectiveness of AI in streamlining record-keeping and improving data retrieval efficiency.
• To establish a transparent review methodology for reproducibility and credibility in AI-archival research.
• To promote interdisciplinary collaboration between artificial intelligence and archival science for future innovation.

Proposed method

• Conducted a systematic literature review focusing on peer-reviewed publications in digital libraries and AI domains.
• Applied predefined inclusion and exclusion criteria to screen studies related to AI in archival science.
• Categorized AI techniques based on their application in archival tasks such as classification, metadata generation, and content analysis.
• Evaluated the methodological transparency and reproducibility of selected studies to ensure review rigor.
• Mapped identified AI applications to core archival functions including appraisal, arrangement, and preservation.
• Used structured reporting to document findings with clear criteria for classification and synthesis.

Experimental results

Research questions

• RQ1 What AI techniques are currently being applied in archival science and records management?
• RQ2 How do AI-driven approaches improve efficiency in archival processes such as appraisal, retention, and data retrieval?
• RQ3 What are the key challenges and limitations in integrating AI into archival workflows?
• RQ4 How transparent and reproducible are the methodologies used in existing AI applications in archival science?
• RQ5 What opportunities exist for interdisciplinary collaboration between AI and archival science to advance the field?

Key findings

• AI techniques such as natural language processing and machine learning are increasingly used to automate metadata generation and content classification in archival repositories.
• AI-driven systems show measurable improvements in data retrieval efficiency, reducing time and effort in locating relevant archival materials.
• The review identifies a growing trend in using AI for automated appraisal and retention scheduling, though methodological transparency remains inconsistent across studies.
• There is a notable gap in interdisciplinary collaboration between AI and archival science, despite strong potential for synergy.
• The study highlights the need for standardized, transparent, and reproducible methodologies in AI applications to ensure trust and scalability in archival practice.
• The review establishes a foundation for future integration of emerging AI techniques into archival workflows, emphasizing ethical and sustainable implementation.