Danvers, Mass. – Copyright Clearance Center, Inc. (CCC), a global licensing and content solutions organization, announces the launch of its text mining solution, RightFind™ XML for Mining. Using the module, commercial life science researchers can create sets of full-text XML articles from more than 4,000 peer-reviewed journals produced by over 25 scientific, technical, and medical (STM) publishers, and import them into their preferred third-party text mining software.
XML for Mining is built on the RightFind™ platform, CCC’s unique suite of cloud-based workflow solutions that offer immediate, easy access to a full range of STM peer-reviewed journal content. Linguamatics I2E text mining software is the first third-party text mining platform integrated with RightFind XML for Mining; integrations with other third-party solutions are planned.
Publishers participating in the offering include Springer Science+Business Media, Wiley, BMJ, the Royal Society of Chemistry, Taylor & Francis, SAGE, Cambridge University Press, American Diabetes Association, American Society for Nutrition, Future Medicine and more. The module is available to businesses through the sales teams of CCC and RightsDirect, CCC’s European subsidiary.
Using RightFind XML for Mining, researchers will be able to identify articles associated with their research from publications to which they subscribe and from those that fall outside their subscriptions.
“The discovery process is enhanced by providing automated access to the many findings that appear in full-text literature, and letting researchers mine content beyond the abstracts,” said Babis Marmanis, CTO & Vice President, Engineering, CCC. “This saves time, and it can also help reduce costs and mitigate an organization’s copyright infringement risk since all of the content is pre-authorized for commercial text mining.”
RightFind XML for Mining enables publishers to facilitate compliant access to article content for life science companies who have been asking for text mining solutions. By participating, publishers have access to usage reports to help them make decisions related to text mining and their content development strategy.
“From working in close collaboration with our corporate customers, we understand the critical need for and opportunities in text and data mining,” said Bettina Goerner, Managing Director Corporate Markets/Databases, Springer Science+Business Media. “By participating, we are not only making our content more discoverable but also helping advance science and innovation by supporting a new solution for commercial text and data mining.”
“RightFind XML for Mining was developed with input from text mining researchers and publishers looking for a voluntary, market-based licensing solution to address new challenges presented by this evolving market,” said Emily Sheahan, GM and Executive Director, CCC. “We will continue to listen to the market, add publisher content and features, and collaborate with valued partners.”
“While text mining scientific abstracts can provide many benefits to scientific research, a huge amount of value is still locked away in full text articles,” said David Milward, co-founder and CTO, Linguamatics. “We believe the integration of our text mining platform, I2E, with RightFind XML for Mining, will significantly simplify and speed up knowledge discovery from full text articles.”
Typically, content from publishers is offered in PDF format, which is poorly suited to the needs of text mining researchers.
“Life science companies struggle to obtain access to full-text content in XML format from multiple publishers,” said Deni Auclair, VP and Lead Analyst, Outsell, Inc. “We’re pleased to see leaders in the STM publishing community working with CCC to help accelerate and significantly improve research efforts.”
Text mining and data mining are methodologies that enable the discovery of knowledge from text materials (unstructured data) and databases (structured data), respectively, through the use of appropriate software. During text mining, researchers use software systems to identify things that they care about (e.g. genes, chemicals, pharmaceutical products, diseases) and relationships between them, for the purpose of discovering new hypotheses, or validating old ones, in a way that would otherwise be very difficult to accomplish.
CCC will conduct live demonstrations of RightFind XML for Mining at the Special Libraries Association (SLA) Annual Conference in Boston June 14-16 in booth 509.