Published: Aug. 23, 2016

The scribbles and highlights made by students reading digital textbooks should allow them to sharpen their learning curve, thanks to new software that can assess how they are digesting academic material and suggest more effective study techniques.

Funded by a four-year, $1 million grant from the National Science Foundation (NSF), the effort will allow for the development of “smart” annotated online textbooks to gain a better understanding of a particular learner’s state of mind and grasp of subject matter. The project was created by the University of Colorado Boulder, Rice University and the University of California San Diego (UCSD).

The study participants will use online textbooks provided by the nonprofit, open-source textbook publisher OpenStax that is based at Rice.

“While traditional textbooks are designed to transmit information from the printed page to the learner, contemporary digital textbooks offer the opportunity to unobtrusively gather information from learners as they read,” explains CU Boulder Professor Michael Mozer, principal investigator on the project. “With a better understanding of a learner’s state of mind, textbooks can make personalized recommendations for further study and review.”

The project is funded by a grant from the NSF’s Cyberlearning and Future Learning Technologies program. The researchers are creating software that will predict how well students will perform on tests based on what they highlight in the digital textbooks.

The researchers also will create tools that use a student’s highlights to create customized quizzes and reviews, said Mozer, a professor in CU Boulder’s Department of Computer Science and a faculty member at the Institute of Cognitive Science.

“Highlighting is something students naturally do on their own, and we want to create software that can use those highlights to improve both their comprehension and knowledge retention,” says Phillip Grimaldi, a co-investigator on the project and research scientist at OpenStax.

Mozer says the research team has adopted a “big-data” approach that involves collecting annotations from a group of learners to draw inferences about individual users. The project leaders will use the data to infer a student’s depth of understanding of facts and concepts, predict test performances and even perform scholastic “interventions” that improve learning outcomes, he said.

OpenStax uses philanthropic grants to produce high-quality, peer-reviewed textbooks that are free online and are used by roughly 680,000 college students at more than 2,000 colleges and universities. The team is asking a large group of OpenStax student users to volunteer their digital textbook highlights for a database that can be mined for clues about their understanding of the text. 

Data from highlights supplied by OpenStax users will enable the research team to create tools that are sensitive to each student’s interests and highlighting choices, said Rice
Professor Richard Baraniuk, a project co-investigator and the director of OpenStax.

“The idea is to reformulate selected passages into review questions that encourage the active re-construction and elaboration of knowledge,” notes Baraniuk.

The research team also includes co-principal investigator and Professor Hal Pashler, who will lead the activities at UCSD.

A modern digital tablet sits atop stacks of books.

“While traditional textbooks are designed to transmit information from the printed page to the learner, contemporary digital textbooks offer the opportunity to unobtrusively gather information from learners as they read,” said CU Boulder Professor Michael Mozer, the principal investigator on the project. “With a better understanding of a learner’s state of mind, textbooks can make personalized recommendations for further study and review.”