presentationposted on 26.05.2021, 19:38 authored by Ken DiFiore
Slides from “Humanities in the information ecosystem"
Unlocking JSTOR & Portico for Text Analysis & Pedagogy
Text analytics, or the process of deriving new information from pattern and trend analysis of the written word, is making a transformative impact in the social sciences and humanities. Sadly, there is a massive hurdle facing those eager to unleash its power: the coding skills and statistical knowledge that text mining requires can take years to develop; moreover, access rights to high quality datasets for text mining are often cost prohibitive and may include further license negotiations. Over the past several years, JSTOR’s Data for Research (DfR) has addressed some of these issues, providing metadata and full-text datasets for its archival content. In January, ITHAKA – the organizational home of JSTOR and Portico – announced a completely new platform that incorporates DfR’s features, as well as adding visualization tools and an integrated analytics lab for learning and teaching text analysis. At NISO Plus, key members of the ITHAKA team will describe the design of this new multifaceted platform and highlight how its components can intersect with the needs of librarians, publishers, educators, students, and faculty. The presenters will emphasize the platform’s hosted analytics lab, where librarians and faculty can create, adapt, and adopt text mining analysis code that works with publisher content for data science instructional sessions.