Adaptive Learning – The Challenges and Developments
Learning analytic is one of emerging technologies that will impact higher education in the next 2-3 years from the Horizon report for higher education just released this week. It refers to pulling data from a variety of data generated as learners interact with the learning contents and environments to give a picture of learners’ profile. According to Horizon report :
Data are collected from explicit student actions, such as completing assignments and taking exams, and from tacit actions, including online social interactions, extracurricular activities, posts on discussion forums, and other activities that are not typically viewed as part of a student’s work. The goal of learning analytics is to enable teachers and schools to tailor educational opportunities to each student’s level of need and ability. Learning analytics promises to harness the power of advances in data mining, interpretation, and modeling to improve understanding of teaching and learning, and to tailor education to individual students more effectively.
Last week, this news was probably the most important one in educational technology. From InsideHigherEd.com “The New Intelligence“: (the Knewton’s approach is explained in this article)
The largest public university in the country, it is hardly fiction. Arizona State University has become ground zero for data-driven teaching in higher education. The university has rolled out an ambitious effort to turn its classrooms into laboratories for technology-abetted “adaptive learning” — a method that purports to give instructors real-time intelligence on how well each of their students is getting each concept.
Big Data stands to play an increasingly prominent role in the way college will work in the future. The Open Learning Initiative at Carnegie Mellon University has been demonstrating the effectiveness of autonomous teaching software for years. Major educational publishers such as Pearson, McGraw-Hill, Wiley & Sons and Cengage Learning have long been transposing their textbook content on to dynamic online platforms that are equipped to collect data from students that are interacting with it. Huge infrastructural software vendors such as Blackboard and Ellucian have invested in analytics tools that aim to predict student success based on data logged by their client universities’ enterprise software systems. And the Bill & Melinda Gates Foundation has marshaled its outsize influence in higher education to promote the use of data to measure and improve student learning outcomes, both online and in traditional classrooms.
In National Educational Technology Plan from Department of Education, it’s stated that digital learning powered by technology is exactly data-driven. The Office of Educational Technology(OET) had initiated an Evidence Framework with an report discussing the promise of sophisticated digital learning systems for collecting and analyzing very large amounts of fine-grained data (“big data”) as users interact with the systems. As this is a new technology for all, the best way to do it : experiment, experiment, experiment.
The report describes an iterative R&D process, with rapid design cycles and built-in feedback loops—one familiar in industry but less so in education (however, the report provides numerous examples of applications in education). An iterative R&D process enables early-stage innovations to be rapidly deployed, widely adopted, and—through continuous improvement processes—refined and enhanced over time. This means that data collection and analysis can occur continuously and that users are integral to the improvement process. The report discusses the promise of sophisticated digital learning systems for collecting and analyzing very large amounts of fine-grained data (“big data”) as users interact with the systems. It proposes that this data can be used by developers and researchers to improve these learning systems and strive to discover more about how people learn. It discusses the potential of developing more sophisticated ways of measuring what learners know and adaptive systems that can personalize learners’ experiences.
The report encourages learning technology developers, researchers, and educators to collaborate with and learn from one another as a means of accelerating progress and ensuring innovation in education.
Before this initiative, another report on “Enhancing Teaching and Learning through Educational Data Mining and Learning Analytics” (Download the Learning Analytics report [PDF, 1.1MB]) had been issued with more details. Online learning technologies offer researchers and developers opportunities for creating personalized learning environments based on large datasets that can be analyzed to support continuous improvement. However, these benefits depend on managing all the data that can now be captured in real time across many students. The challenges include :
Technical Challenges : Lack of data interoperability among different data systems imposes a challenge to data mining and analytics that rely on diverse and distributed data. Over time, piecemeal purchases of software can lead to significant decentralization of the source of education data, such as student information systems, teachers’ online grade books, homework submission systems, and publishers’ online assignments, homework help, and assessments.
Limitations in Institutional Capacity : In reports about the newest technologies for adaptation, personalization, and recommendation, the role of human judgment is sometimes underemphasized (with the exception of visual data analytics). All the experts consulted for this issue brief emphasized the key role that people play in many steps of the data mining and analytics process. Smart data consumers can help determine what questions to address, what data to collect, and how to make reports meaningful and actionable. They can also help interpret data, discern and label patterns, and guide model building.
Privacy and Ethics Issues : Educational data analysts should share their insights with those who can benefit from them (for example, students, teachers, and school districts), and what is shared must be framed in a way that benefits rather than harms. Policymakers bear an ethical responsibility to investigate the validity of any predictive model that is used to make consequential decisions about students.
More about OET’s Education Data Initiative can be found here. On October 9, 2012, the White House and the U.S. Department of Education hosted an “Education Datapalooza” showcasing entrepreneurs and innovators working with open educational data to improve educational outcomes. Open educational data can take many forms, including school performance data, lists of grant applicants, specifications such as the Learning Resource Metadata Initiative (LRMI), data standards such as the financial aid shopping sheet template, and even data about learning resources.