Data-driven tools, real-time feedback hold great promise for helping teachers and students, but obstacles stand in the way, Brookings report says.
Data mining and data analytic software could help students by providing real-time feedback about their academic performance. In addition, teachers could use big data-based tools to study their pupils' learning patterns and to tailor lessons to meet the needs of individual students.
In the report, West explained how educational tools incorporating real-time data could provide immediate feedback to students and teachers. For instance, a software program that teaches reading could collect data on how long it takes each student to read a particular story. Quizzes would tell students immediately if their answers are correct--relieving teachers of the tedious, time-consuming chore of grading papers--and compare each pupil's performance to classmates and students nationwide.
Teachers would benefit too, West said. Real-time tools could produce reports that detail each student's reading time and comprehension, vocabulary skills, and use of supplemental tools such as websites that provide additional detail on specific words and concepts. These big data techniques could help educators evaluate students' actions, including the length of time spent reading, and how quickly each pupil learns key concepts.
"So-called 'big data' make it possible to mine learning information for insights regarding student performance and learning approaches. Rather than rely on periodic test performance, instructors can analyze what students know and what techniques are most effective for each pupil. By focusing on data analytics, teachers can study learning in far more nuanced ways," West wrote.
In addition to gauging student performance on the fly, data mining and analytic software can help educators study patterns that predict other outcomes. Experiments conducted at Carnegie Mellon University, for instance, provide tools that professors use to create online tutorials in such subjects as chemistry and physics, as well as pre- and post-test assessments and records of students' interactions with electronic tutors.
"The system sends error messages if the student follows an incorrect approach and provides answer hints if requested by the student. Instructors can get a detailed analysis not just of whether the student reached the final answer correctly, but how they solved the problem," wrote West.
A technology-driven education system supported by vast amounts of data may seem cold and impersonal, but research suggests the opposite is true.
WebQuest, for instance, is a Web-based educational tool that sends students online to solve specific problems or to research information. Its purpose is to teach students to find and evaluate online materials. A study of 139 teachers who attended a WebQuest instructional conference showed that most instructors find these types of projects very effective.
Their students, in fact, enjoyed the WebQuest's "collaborative and interactive nature. As opposed to looking for general Internet information on their own, students had to talk with one another to fulfill the assignment," West wrote.
Data-driven educational tools are already in use throughout much of the U.S, the report said. Schools in 16 states, for instance, use data-mining techniques to identify at-risk students. By using prediction models for key factors such as truancy, disciplinary problems, and changes in course performance, educators can identify those students most likely to drop out.
Data visualization tools show potential as well. Dashboards, for instance, display key metrics in a simple user interface, allowing school administrators to visually see how their students are performing overall.
There are many obstacles to widespread implementation of big data tools in schools, however, including budget cutbacks, incompatible information systems, a lack of understanding of the potential of data-driven techniques, and privacy concerns.
"It will not be easy to overcome these challenges," wrote West. "Creating data-sharing networks necessitates the balancing of student privacy on the one hand with access to data for research purposes on the other."
High-frequency trading (HFT) has been in the spotlight recently as market participants have debated the value of HFT for investors. While only a certain number of players compete at the ultra-low latency level, many other players are taking advantage of technologies utilizing models and strategies that leverage new data sets as well as more types of information. Join Wall Street & Technology for the HFT Under Attack webcast to find out the opportunities of using big data in a trading strategy. It happens Sept. 12.
6 Tools to Protect Big DataMost IT teams have their conventional databases covered in terms of security and business continuity. But as we enter the era of big data, Hadoop, and NoSQL, protection schemes need to evolve. In fact, big data could drive the next big security strategy shift.
Big Data Brings Big Security ProblemsWhy should big data be more difficult to secure? In a word, variety. But the business won’t wait to use it to predict customer behavior, find correlations across disparate data sources, predict fraud or financial risk, and more.
Join us for a roundup of the top stories on InformationWeek.com for the week of April 24, 2016. We'll be talking with the InformationWeek.com editors and correspondents who brought you the top stories of the week!