Gale Digital Scholar Lab: Support

The Lab is a single research platform where you can apply natural language processing tools to raw text data (OCR) from your institution's Gale Primary Sources holdings, or from uploaded OCR. Gale Digital Scholar Lab is organized in three broad steps: Build, Clean, and Analyze. These steps support newcomers and experienced users alike as they interpret both Gale Primary Sources and their own documents. An integrated Learning Center provides instructional tutorial videos and explanations throughout. The six built-in analysis tools are: Ngrams, Sentiment Analysis, Topic Modeling, Named Entity Recognition, Document Clustering, Parts of Speech.

• Single Platform Text and Data Mining (TDM) Environment - Gale’s unparalleled Primary Sources (GPS) collections are available alongside familiar open source text mining and natural language processing tools, removing two of the key barriers to entry in the digital humanities: finding and curating a quality content set, and the appropriate (and accessible) digital tools with which to analyze it.
• Create bespoke content sets - Greatly reduces the effort and time needed to create, clean, parse, and analyze large sets of archival text data.
• Cloud-Hosted, Optimized Data - Gale’s OCR data is optimized for text mining; providing the institution’s Gale Primary Sources data in one place, without the concern of hosting and managing it. Gale Digital Scholar Lab makes the institution’s Gale collections more widely accessible and opens up digital scholarship to more researchers.
• Tools familiar to the DH community - Gale Digital Scholar Lab brings together tools from various Open Source providers and a streamlined user interface that allows customization of the analysis tools according to particular research needs.