Jim Salmons’ Response to the DHUnbound’s ‘Computational Periodicals’ Unconference Two Kick-off Questions
I am excited to be participating in the “A Computational Periodicals Unconference: Exploring New Opportunities for Critical and Collaborative Inquiry” session on May 18th during the #DHUnbound2022 conference hosted by the Association for Computers and the Humanities (ACH). The session organizers are Sarah Salter, Ben Lee, Joshua Ortiz Baco, and Jim Casey.
The Unconference is designed as a kind of “speed-dating” event to encourage participants’ sharing of research interests and activities to facilitate the establishment of specific project collaborations, and to kick-start the formation of a community of practice for the computational periodicals research community within the Digital Humanities domain.
In a pre-event communication the organizers informed participants that a context-setting exercise for this Zoom-based virtual event will involve a round-robin sharing of our answers to two specific questions. As it is my hope to gain maximum value from this unique event, I have drafted my response to those questions so as not to fumble when it is my chance to speak to the group. This event is a golden opportunity for me to find kindred spirits, and establish my interest in participating in the formation and growth of this research community.
Q1: What would you hope to get out of a growing computational periodicals community?
I am a 71-year-old unaffiliated Citizen Scientist focused on the development of a Ground Truth Storage format for serial publications supporting an integrated model for complex document structures and content depiction based on an ontological stack of CIDOC-CRM, FRBRoo, PRESSoo, and PAGExml using a metamodel subgraph design pattern.
The goal of my research is to help move the focus of digitization technology research from within-page to whole-issue layout recognition in support of cultural heritage text- and data-mining. To this end, my specific focus is on implementation of a reference model implementation of the MAGAZINEgts format for the collection of the 48 issues of Softalk magazine, and more generally, on the exploration of the over 33,000 issues in the Computer Magazines collection at the Internet Archive.
My motivation for participation in this community is to find kindred spirits to facilitate my personal learning, and collaborative partners interested in the goals and focus of my Digital Humanities research. I particularly value opportunities to work with students and early career faculty interested in independent and course related projects that align with my research agenda.
Q2: What could you offer or contribute to a growing computational periodicals community?
As an unaffiliated Citizen Scientist, I lack deep knowledge of the digitization technology and machine learning domains. However, I can share my unbridled passion for my focus on whole-issue document layout recognition and Ground Truth dataset development. As I am not a working academic or research professional, I am not burdened by the many competing draws on my time and energies. And I am particularly skilled at innovative thought leadership and project promotion.
An example project of my current focus on whole-issue document structure recognition is the MagTOCml project. The goal of this project is the development of a Ground Truth dataset of Computer Magazine TOCs, or Table of Contents, pages for use in Machine Learning model training. This dataset will be invaluable for text- and data-ming of the vast trove of Computer Magazines at the Internet Archive.
Supplemental Information About Me and My Digital Humanities Research
I recently did an invited Lightning Talk at the “Library as Laboratory” webinar series at the Internet Archive. This four-minute video is a whirlwind introduction to my post-cancer rebirth as a Digital Humanities Citizen Scientist.
Our DATeCH Posters & NewsEye Conference Panel
Links to Relevant Articles
More on Our Digital Humanities Research
My GitHub Digital Humanities Project Tools and Datasets
- https://MagTOC.ml (project website)
- https://github.com/MagTOCml (dataset and tool repositories)
- https://bit.ly/MAGAZINEgts-Softalk-Ads-dataset
More on Our Citizen Scientist Advocacy
More on Our GitHub Copilot for Disabled Developers Project
Jim Salmons is a seventy-one-year-old post-cancer Digital Humanities Citizen Scientist. His primary research is focused on the development of a Ground Truth Storage format providing an integrated complex document structure and content depiction model for the study of digitized collections of print era magazines and newspapers. A July 2020 fall at home resulted in a severe spinal cord injury that has dramatically compromised his manual dexterity and mobility.
Jim was fortunate to be provided access to the GitHub Copilot Technology Early Access Community during his initial efforts to get back to work on the Python-based tool development activities of his primary research interest. Upon experiencing the dramatic positive impact of GitHub Copilot on his own development productivity, he became passionately interested in designing a research and support program to investigate and document the use of this innovative programming assistive technology for use by disabled developers.
