Home | Connectors | OpenText Magellan Text Mining Engine | OpenText Magellan Text Mining Engine - ArchivesSpace Integration and Automation
OpenText Magellan Text Mining Engine is well suited for extracting entities, topics, and relationships from large volumes of unstructured content, while ArchivesSpace is used to manage archival descriptions, collections, and access to historical records. Integrated together, they can help archives, records teams, legal researchers, and compliance groups surface hidden value in collections, improve discovery, and streamline review workflows.
Data flow: OpenText Magellan Text Mining Engine to ArchivesSpace
Magellan can analyze digitized correspondence, reports, manuscripts, and scanned finding aids to identify people, organizations, places, dates, and subjects. Those extracted entities can then be used to enrich ArchivesSpace collection records with additional descriptive metadata.
Data flow: OpenText Magellan Text Mining Engine to ArchivesSpace
Many archives contain legacy documents with limited description. Magellan can process these materials to identify recurring themes, named individuals, and organizational references, then pass structured outputs into ArchivesSpace to support more complete archival descriptions and indexing.
Data flow: Bi-directional
ArchivesSpace can provide collection descriptions, series notes, and item-level metadata to Magellan for analysis, while Magellan can return extracted concepts and relationship maps that help users discover related collections, people, and topics. This creates a richer research experience for internal staff and external patrons.
Data flow: ArchivesSpace to OpenText Magellan Text Mining Engine
Before archival materials are opened to researchers, ArchivesSpace records can be sent to Magellan to detect sensitive entities such as personal names, legal references, confidential projects, or regulated topics. Review teams can use the results to prioritize records for restriction, redaction, or further legal review.
Data flow: ArchivesSpace to OpenText Magellan Text Mining Engine
ArchivesSpace can supply inventory data, folder lists, and existing descriptions to Magellan, which can then analyze content patterns across collections. Processing teams can use the output to identify high-value collections, recurring topics, or records likely to support institutional research priorities.
Data flow: OpenText Magellan Text Mining Engine to ArchivesSpace
Magellan can extract relationships from letters, reports, and case files, such as who communicated with whom, which organizations were involved, and what events were referenced. Those relationship insights can be stored or referenced in ArchivesSpace to improve contextual description and cross-collection linking.
Data flow: Bi-directional
ArchivesSpace can provide collection counts, accession data, and descriptive fields, while Magellan can analyze the underlying text to generate topic trends, entity frequency, and subject clusters. Combined outputs can feed reporting dashboards for leadership, curators, and records managers.
Together, OpenText Magellan Text Mining Engine and ArchivesSpace can transform archival content from static descriptions into searchable, analyzable, and operationally useful information. The integration is especially valuable for institutions managing large legacy collections, sensitive records, or high-volume research requests.