The need to accurately classify records is a core problem in many domains. Historically, the classification of records was done manually as records were received and then categorized. Unfortunately, due to a significant growth in the volume of records, the need for robust auto-classification methods that can effectively “read” and classify records, is high. Today, significant challenges remain with the development of effective auto-classification processes for records. This is because the records traditionally require functional classification based on context, not topic classification based on content. Functional classification traditionally has been a challenge for both humans and machines, with little research on how to classify a record effectively functionally. To move research forward, this paper will address the challenges of both human and machine classification of records.Firstly, this paper will seek to evaluate the efficacy of human manual classifiers on a classification task, using knowledge from this process to articulate a process for automated functional classification that utilizes a record’s archival diplomatic context. Secondly, this paper will compare the efficacy of manual versus machine (i.e., auto-classification) using a record set with over 500,000 records, using a novel auto-classification approach that leverages a record’s context, not just its content, to improve classification accuracy. As this paper will discuss, there is significant variance between expert human (i.e., records managers) during the manual classification process, with statistically significant differences in their ability to accurately classify both administrative and operational records. Moreover, this paper will demonstrate that an auto-classifier, when trained using key elements of context, can statistically outperform a group of expert human classifiers on a classification task.

The need to accurately classify records is a core problem in many domains. Historically, the classification of records was done manually, with those records "read" as they were received and categorized. Unfortunately, due to a significant growth in the volume of records, the need for robust auto-classification methods that can effectively "read" and classify records, is high. Today, significant challenges remain in the literature and practice relating to the development of effective, auto-classification processes. This is because the functional classification process is a challenge for both humans and machines, with little research on the steps needed to effectively functionally classify a record. In order to move research forward, this paper will address both challenges. Firstly, this paper, will seek to evaluate the efficacy of manual classifiers on a classification task, using knowledge from this process to articulate a process for functional classification that utilizes a record’s archival diplomatic context. Secondly, this paper will compare the efficacy of manual versus auto-classification using a record set with over 500,000 records, using a novel auto-classification approach that leverages a record’s archival diplomatic context, and not just its content, to improve classification accuracy. As this paper will discuss, there is significant variance between records managers during the manual classification process, with statistically significant differences in their ability to accurately classify both administrative and operational records. Moreover, this paper will demonstrate that an auto-classifier, when trained using key elements of archival diplomatic context, can statistically outperform a group of expert manual classifiers on a classification task.

The need to accurately classify records is a core problem in many domains. Current methods for auto-classification focus on a record's content and not its context. As a result, current auto-classification methods are unable to achieve the levels of precision, accuracy, and recall that match or exceed the levels generated by human classifiers. In order to address this challenge, a new methodology is needed that specifies how to extract contextual features from a record in order to improve the auto-classification accuracy, precision, and recall of records at scale. This paper closes this gap, using the diplomatic definition of context to specify a mapping that will operationalize the capturing of context from a record. This mapping, makes it possible to continue developing a formal method for functional auto-classification and contextual feature extraction that will utilize a record's context to improve functional auto-classification accuracy, precision, and recall.

Over the past 10 years, digitization, big data, and technology advancement has had a significant impact on the work done by computer scientists, information scientists, and archivists. Together, each of these groups has contributed to unlock new areas of trans-disciplinary research that are critical for forward progression in the world of big data, while collectively spurring the creation of a new inter-disciplinary field - Computational Archival Science (CAS). Unfortunately, significant gaps exist, including the lack of a comprehensive definition of CAS. This paper closes those gaps by proposing a new, comprehensive definition of Computational Archival Science (CAS) while simultaneously highlighting key big data challenges that exist both in industry and academia. The paper also proposes important areas of future research especially in the context of big data and artificial intelligence.

Archivists and records managers would benefit from a greater understanding of the use and effectiveness of various machine learning methods, especially in the related context of electronic discovery. However, the binary classification methods used in advance search techniques in the e-discovery space may or may not prove efficacious where the information task involves sorting records into multiple categories. A survey of the landscape of machine learning methods reveals areas of potential weakness, which in turn serve as a starting point for future research in the computational archives space.