Search

Many libraries and archives maintain collections of research documents, such as administrative records, with paper-based formats that limit their access to in-person use. Digitization transforms paper-based collections into more accessible and analyzable formats. As collections are digitized, there is an opportunity to incorporate deep learning techniques, such as Document Image Analysis (DIA), into workflows to increase the usability of information extracted from archival documents. This paper describes our approach using digital scanning, optical character recognition (OCR), and deep learning to create a digital archive of administrative records related to the mortgage guarantee program of the Servicemen’s Readjustment Act of 1944, also known as the G.I. Bill. We used a collection of 25,744 semi-structured paper-based records from the administration of G.I. Bill Mortgages from 1946 to 1954 to develop a digitization and processing workflow. These records include the name and city of the mortgagor, the amount of the mortgage, the location of the Reconstruction Finance Corporation agent, one or more identification numbers, and the name and location of the bank handling the loan. We extracted structured information from these scanned historical records in order to create a tabular data file and link them to other authoritative individual-level data sources. We compared the flexible character accuracy of five OCR methods. We then compared the character error rate of three text extraction approaches (regular expressions, document image analysis, and named entity recognition). We were able to obtain the highest quality structured text output using DIA with the Layout Parser toolkit by post-processing with regular expressions. Through this project, we demonstrate how DIA can improve the digitization of administrative records to automatically produce a structured data resource for researchers and the public. Our workflow is readily transferable to other archival digitization projects. Through the use of digital scanning, OCR, and DIA processes, we created the first digital microdata file of administrative records related to the G.I. Bill mortgage guarantee program available to researchers and the general public. These records offer research insights into the lives of veterans who benefited from loans, the impacts on the communities built by the loans, and the institutions that implemented them.

Even as southern Appalachian migrants began to actively assert a group identity in some northern cities in the late 1960s, it was an open question as to whether they ought to be considered a group at all. In the years since the 1960s, the fate of southern Appalachian migrants in the North and Midwest has continued to be the subject of much debate. Migrants from the southern Appalachian region were clearly a group apart in the broader southern white exodus. In socioeconomic terms, Appalachian migrants looked like international immigrants from all over the world. If non-Appalachian southerners most closely resembled migrants from Canada and Western Europe, Appalachian migrants' economic experiences were more like those of migrants from Korea, South America, and Eastern Europe. In great contrast to the overwhelmingly successful southern white migrants portrayed in some recent historical studies, migrants from the Appalachian South seem to have been just as much at risk as nearly any other group of newcomers short of southern African-Americans and the most impoverished international immigrant groups., Minnesota Population Center Working Paper Series