"Text and Data Mining (TDM) refers to automated research techniques and strategies, designed to identify trends and patterns in large sets of data. (Text mining is truly just a certain flavor of data mining, focusing on [patterns found] in large data sets comprised of text.)
These techniques are increasingly finding useful applications in a variety of disciplines, allowing for findings not feasibly possible through traditional methods of analysis. For instance, researchers in Digital Humanities have been able to broaden their textual analysis of wide swaths of literature, while scientists can speed analysis of data and text to hasten the progress of science."
From the University of California Los Angeles Library Text and Data Mining Research Guide
Many ODU library resources have licenses that restrict text and data mining on the materials. You should avoid using automated methods for downloading content (including robots, spiders, web scraping, etc.) as most publishers do not allow this.
Always refer to the terms-of-use of any resource with which you intend to conduct a TDM project.
The Yale Resources for Text and Data Mining: Finding Texts and Data (currently unavailable) cautions that:
"Before you get started finding texts or data for text and data mining, be aware that programmatically accessing information isn't necessarily permitted everywhere that it is possible. Think about questions of copyright, how you're accessing data, and who might have a stake in that data before you embark on a project."
Refer to the ODU Libraries Databases tab for more specific information about library resources.
The ODU Libraries maintains this guide as a starting point for faculty, students, and researchers interested in TDM projects, and is mostly geared towards those interested specifically in text mining.
This guide provides:
Please be aware that the libraries do not currently have the capacity to provide assistance with TDM techniques or analyses, or negotiations with vendors for individual projects.
While we will do our best to keep this guide up to date, always check licensing agreements and/or terms and conditions of the specific resource you wish to use before you begin a text or data mining project.
This guide is intended for informational purposes only and does not constitute legal advice.
For more in-depth legal information: contact the Office of University Counsel.
