2015 Charleston Library Conference

Data mining methods enable researchers to recognize patterns within a mass of texts, but the same methods can also offer a more targeted glimpse on a smaller scale. As text and data mining become further embedded in contemporary research practices, navigating and mapping out the process will become increasingly vital. This session will offer an overview of the licensing, commercial, and research-oriented lessons learned during a collaborative data mining pilot conducted between Syracuse University Libraries and ProQuest.

The pilot project at Syracuse University mobilized a range of teams at both organizations to facilitate data mining research centered on a question best answered though keen attention to one historical periodical’s presentation of a single specific type of information over time. During the course of this partnership, both Syracuse University Libraries and ProQuest encountered a range of questions surrounding content rights, internal workflow processes, data distribution models, and data mining skill sets.

The panel of presenters will share their first-hand experience and discuss how they worked together to address each road-block in order to help others learn to navigate some of the challenges and opportunities raised by the proliferation of data-driven research within the academy.