Greg Jansen

Greg Jansen is a Senior Research Software Architect at the University of Maryland's College of Information Studies. He is affiliated with the Applied Research Lab for Intelligence and Security (ARLIS) and the Advanced Information Collaboratory (AIC). His research focuses on applying computer vision, machine learning, and data science to challenges in archival science, digital humanities, and information systems. Notable projects include developing the Brown Dog data transformation ecosystem, enhancing access to historical records, and creating frameworks for collaborative computational archival education.

Key research interests include digital curation at scale, autocuration infrastructure, and the ethical use of cultural big data. His work spans government records analysis, census data sifting, and preservation of legacy systems like punchcards. Recent projects emphasize linking disparate datasets (e.g., WWII incarceration biographies) and building scalable cyberinfrastructure for billion-record archives.

Publications highlight trends in applying AI-driven methods to historical data challenges, designing open-source tools for repositories, and ensuring equitable access to archival materials. Collaborations include work with the World Bank on social media analytics and international institutions to create transparency portals for sensitive datasets.

Jansen leads technical development for initiatives like the 'Window Into Neuroregulation' (WIN) project and has pioneered frameworks for distributed historical data distribution (DRAS-TIC Linked Data). His contributions bridge software architecture with archival practice, advancing both technical and scholarly outcomes in information science.