Gale recently debuted new personalization and visualization features for its Digital Scholar Lab (DSL)—a cloud-based research environment designed to facilitate the access and analysis of Gale primary source materials and a researcher’s local humanities and social sciences collections. The seven tool updates expand text and data mining (TDM) research possibilities for students, faculty, and librarians, including:

Sentiment by Timeframe: Researchers can now use the DSL’s Sentiment Analysis tool to visualize data within their content sets across different timeframes, ranging from a single month to centuries.

Mark-Up View for Parts of Speech and Sentiment Analysis Tools: This new feature provides additional context for results by allowing users to see how words are identified in their documents.

Parts of Speech Pie Chart: This new visualization option for the Parts of Speech tool enables users to see data in different ways, such as what percentage of a work or content set is made up of nouns.

Personalized Lexicons for Sentiment Analysis: Currently, DSL’s Sentiment Analysis tool uses AFINN—a list of English words created by Finn Årup Nielsen using tweets about the United Nations Climate Conference between 2009 and 2011, with words “scored” for positive or negative emotions or sentiment. This new feature enables users to upload their own custom lists of words to tailor analysis to specific materials and subjects, including non-English TDM with support for accented characters.

Ngrams Start Word Lists: This new feature enables users to create an Ngram (in this case, words or sequences of words) visualization for a list of words they’re interested in, returning frequencies for only those terms within their content set.

Ngrams Over Time: Launching this month, this feature will provide the frequency and distribution of Ngrams in a content set over time.

Color Palettes: Also launching later this month, this new feature will enable users to customize the appearance of visualizations for presentations and/or inclusion in articles.

Gale is “constantly building features based on user feedback,” Becca Gillott, product manager for Gale Digital Scholar Lab, told LJ. In addition to the Gale Digital Humanities User Engagement Group, which gives the company feedback “at every point of our development process,” Gillott said that “we also focus…on what we’re hearing from customers and users who are using it as part of their course or part of their teaching. What features are they asking for?... That’s really our drive—making sure that we’re meeting user needs and that we’re expanding the possibilities of research that you can do with the lab.”

The new Personalized Lexicons for Sentiment Analysis feature is one example. The AFINN lexicon was designed using social media, Gillott noted, but “if you’re looking at—even Margaret Thatcher [letters] in 1975, words that are positive and negative on Twitter were maybe not positive and negative in 1975. And if you keep tracking that backwards into, say, the 18th century, those terminologies don’t always match up. Ultimately, the person who is best positioned to say what is the right positive and negative terminology for the content I’m looking at is the researcher.”

Separately, Gale also announced the launch of “Introduction to Digital Humanities,” a new online course for undergraduate students embedded in DSL that teaches text and data mining along with digital and data literacy skills. The course includes six modules: using digital archives, mining text and data, building content sets, cleaning data, analyzing data, and creating and publishing projects.

Sarah Ketchley, senior digital humanities specialist for Gale, explained that the new course aligns with Association of College and Research Libraries (ACRL) standards for digital literacy as well as Bloom’s Taxonomy—the hierarchical framework for categorizing educational goals. The course moves “from basic understanding right through to creative implementation of a particular theme or topic,” Ketchley said. “We wanted to provide something that was aligned with the work that is being done in the [Digital Scholar] Lab. So, we focused on developing an understanding of digital archives, what they are, [and] how to use them in digital humanities…. obviously using Gale Primary Sources as a starting point, but broadening to look at the field of working in archival studies more generally.”