Infotrieve, Inc. (www.infotrieve.com), the leader in global-enterprise SaaS software and business services for scientific, technical and medical (“STM”) published content access and management, today announced that it has completed a pilot project that included the successful implementation of a beta text mining solution leveraging the capabilities of the Mobile Library platform. Infotrieve partnered with long standing client, global biopharmaceutical leader UCB, to develop a solution aimed at providing a cloud-based text mining platform that would allow UCB staff to mine full text articles from multiple publishers using a variety of popular text mining tools in a standardized, copyright compliant and end user friendly manner.
Andrew Clark, Head of Global Information & Competitive Intelligence Services of UCB commented on the initiative: “Text mining is about structuring the unstructured to help researchers derive further insight from published information. In the workflow it is critical that the information is available in the right format and accessible in an aggregated and copyright compliant manner. Working closely with Infotrieve and some of our main publishers gave us an opportunity to understand some of the common challenges that researchers face and evolve a solution. The concept of text mining whilst growing in popularity is still relatively new and there is much education and learning to be done to get everyone in the right place. The future is exciting though and great progress is being made.”
In completing the pilot Infotrieve collaborated with six major life science publishers, collecting from each hundreds of full text articles in Extensible Markup Language (XML) format. Infotrieve tagged each article using Journal Article Tags Suite (JATS), thereby creating a standardized and homogenized corpus for text mining, and loaded the resultant articles into its cloud-based Mobile Library platform. The Mobile Library’s flexible search capabilities, content management tools and powerful rights management engine provided pilot participants the ability to search and create a research set, and then further refine the results to clearly identify articles currently under subscription versus those requiring purchase, as well as those available for text mining.
“Text mining is increasingly important to many of our clients, particularly those in the life sciences, as the process can help uncover previously unmatched relationships between symptoms, compounds and patient outcomes, and ultimately speed up therapeutic discovery,” said Ken Benvenuto, President and Chief Executive Officer of Infotrieve. “We are excited to have the opportunity to work with UCB and in concert with the publishing community on the initiation of this innovative text mining effort, and are looking forward to its continued development.”
Infotrieve’s Mobile Library already houses a sophisticated content management engine offering cloud-based access to an organization’s full suite of information assets, maximizing access to electronic subscriptions, databases and enterprise repositories. The platform also includes a comprehensive rights management suite, sophisticated content usage analytics, as well as a high quality and cost effective document delivery solution supported by the world’s largest collection of published STM research.