Researchers will now be able to uncover new connections and make new discoveries using ProQuest’s TDM Studio service, a pioneering end-to-end solution for text and data mining. TDM Studio puts the power of text and data mining directly into the researcher’s hands, from their initial idea to their final output.
With this new solution, creating a content set has been reduced to hours, rather than the months required with traditional approaches. TDM Studio gives researchers the freedom to use the content, methods and tools they prefer – and to collaborate on projects both within and outside their university.
TDM Studio unlocks a vast collection of current and historical ProQuest content (including news, journals dissertations and theses, primary sources and more) for TDM. Researchers also have the option to incorporate content from other sources, and to utilize their preferred methods with open source programming languages such as R and Python – along with methods provided by ProQuest – for analysis and visualization.
“The use of text and data mining in academia is enabling researchers in all disciplines to make breakthroughs that have never before been possible,” said Mindy Pozenel, Director of Product Management for ProQuest TDM Studio. “With its flexibility and ease of use, TDM Studio helps researchers bypass the cumbersome mechanics of text and data mining and get straight to the point: answering their research questions. TDM Studio has also been designed as an ideal solution for teaching and learning.”
Librarians can use TDM Studio to further leverage their existing wealth of content, creating more ways to partner with research teams and enhance teaching and learning.
Caleb Rawson, Assistant Professor of Accounting at the University of Arkansas, is using TDM Studio for a project that analyzes how public firms communicate information and how that information is reported in the media. “One of my greatest research challenges is working with a corpus of millions of news articles, organizing the relevant content and matching it to other data,” he said. “TDM Studio is helping me find patterns in data in a way that’s consistent, reliable, and in a way that makes sense.”
“The use of text and data mining greatly increases the number of important questions we can answer,” said John Eric Humphries, Assistant Professor of Economics at Yale University, who is using TDM Studio to analyze dissertations for a project related to human capital. “ProQuest has been an amazing partner in setting up a TDM infrastructure that is both powerful and easy to use.”
“In the medical field, we often don’t have the manpower to go through tedious manual processes to analyze data, which can be frustrating,” said Sunmoo Yoon, Associate Research Scientist at Columbia University, who is working on a project that uses Twitter to provide culturally sensitive support to dementia caregivers. “By text mining a large corpus of material, TDM Studio is helping us learn the right words and phrases to help target caregivers with self-care and self-management messages, reducing their risk of loneliness and depression.”
In addition to Yale, Columbia and the University of Arkansas, nine other institutions globally partnered with ProQuest and contributed to the development of TDM Studio. Several early-access customers are already using TDM Studio, and ProQuest is currently recruiting additional early users.