Text data mining (TDM) is the application of computational methods to analyze a large set of texts to discover patterns and trends. SMU Libraries and OIT offer introductory workshops and tutorials for you to learn the basic skills and tools necessary to get started with text data mining.
Using library databases for text data mining requires specific licensing. Some library databases have licensing already in place, but most require additional licensing and funds.
Each publisher has specific access rules and licensing requirements. They may require you to use specific tools, they may want to conduct the process themselves, or they may have limitations on the amount you are allowed to download. Most databases require additional licensing and funds.
Library licenses do not generally permit web scraping of database content. If you do not see a request form or API, contact us so we can determine licensing for that product.
We can help you find and negotiate with vendors if you need to acquire data. We work on a case-by-case basis to purchase datasets for researchers and prioritize data with permanent rights and multi-user licenses.