Two universities discuss their partnership with Realizeit investigating predictive analytics within the context of adaptive learning. We will discuss the methods behind our research and also the implications of our findings for improving course design and addressing student success using adaptive learning.
Adaptive learning and predictive analytics both offer promise for increasing success, especially for the higher education underserved and academically struggling student populations. The troubling fact remains, however, that in spite of all our technology advances if you are a student from a family that resides the bottom economic quartile your probability of graduating from college is less than 10 percent. Mullainathan and Sharif summarize the problem this way:
“Scarcity can be defined as having far more needs than resources. Consider the lives of students living at or near the poverty line— they may be working two part-time jobs with no benefits and so are unable to take a full course load. Health costs are a significant burden. They may also have childcare expenses in addition to tuition and other costs, such as textbooks. Most likely they borrow money to attend school and may be unable to search for additional financial assistance because of time or resource constraints. Transportation is an additional problem; public transportation creates a time crunch, while a car adds additional expenses.
These students are caught in the scarcity trap that depletes their cognitive bandwidth. They have comparable abilities to their more affluent peers, but the demands and stresses of their lives prevent those young people from effectively using those abilities. They have no slack, either cognitive or financial, in their lives, causing them to juggle so many things that they cannot devote the time and effort required by their courses. What does this have to do with higher education and adaptive learning?
What happens when a loaded and depleted student misses class? What happens when her mind wanders in class? The next class becomes a lot harder. Miss one or two classes and dropping out becomes a natural outcome, perhaps even the best option, as she no longer really understands much of what is being discusses in class. A rigid curriculum—each class building on the previous—is not a favoring setting for students whose bandwidth is overloaded. Miss a class here and there and our student had started a slide from which she is unlikely to recover. … Linear classes that must not be missed can work well for the full time student; they do not make sense for the juggling poor.”
In contrast, consider an effective analytics process within an adaptive learning curriculum where modules are supported by learning nodes and a go-at-your-own-pace effective course design. With effective prior prediction of success, an adaptive learning course can place a student at the optimal starting point corresponding to her estimated competency level.
A University and Platform Provider Partnership
The University of Central Florida and Colorado Technical University, working with Realizeit their common adaptive learning platform provider, began examining the student success problem within adaptive learning instruction. The institutions (considerably different in organization, student population, and cost structure) worked together with Realizeit to investigate how adaptive learning might address the student success challenges.
University of Central Florida (UCF)
The University of Central Florida is one of 12 public universities in Florida’s State University System. Located in Orlando, the university is the largest in Florida with over 68,000 students. UCF is a Hispanic serving institution with an average age of 24 with 22% of students over the age of 25.
In 2014, UCF began investigating adaptive learning as a means to improve student success. Realizeit is the university’s enterprise platform, allowing faculty control and flexibility over course content. A team of Personalized Adaptive Learning (PAL) instructional designers at UCF’s Center for Distributed Learning (CDL) provides support and guidance to faculty as they implement the course design process. Faculty who wish to use adaptive learning participate in a faculty development program (PAL6000) and are assigned an instructional designer who is experienced with Realizeit. The support team provides assistance with the workload of adaptive course creation ensuring quality design. CDL also provides video, graphics, and technology support as faculty redesign and teach their adaptive course.
Colorado Technical University (CTU)
Colorado Technical University is a for-profit university providing industry-relevant programs to a diverse student population of approximately 25,000 students. The university began offering online courses in 2000 and now offers over 50 online or blended programs. The older student population has an average age of 36 and is 60% female.
CTU’s open enrollment results in students who enter with varying levels of expertise; therefore, the university began investigating adaptive learning in 2012. The ability of this approach provides students with unique learning paths that adjust to their varied knowledge and preferences to improve CTU’s nontraditional students’ online instructional experience. They are introduced to adaptive learning during orientation and, if needed, are provided help guides and additional training in using the technology. Also, faculty must successfully complete a separate asynchronous training prior to teaching a course with adaptive technology.
The Adaptive Learning Partner: Realizeit
Realizeit is both an adaptive and adaptable learning platform. Institutions can bring their existing courses into Realizeit and make them adaptive, or they can build adaptive courses from scratch. The platform is adaptable in that it does not impose a pedagogical approach on the course but can be customized to suit the needs of each instructor, course or institution. The platform supports approaches ranging from competency-based learning to self-directed models, as well as various models of learning in corporate settings.
The principle underlying all these approaches in Realizeit is the separation of curriculum from content. Traditionally, learning is content driven, with structure typically dictating the same linear pathway through the material for all students. In Realizeit, the curriculum drives the direction of learning and uses content to help students acquire knowledge. The platform defines the curriculum using a hierarchical model and a structure known as the Curriculum Prerequisite Network--a directed acyclic graph where the nodes represent the concepts to be learned, and the boundaries represent the prerequisite relationships that exist between them. Thus, Realizeit creates a map that shows a student many non-linear pathways to move through the concepts.
Just as an instructor can teach a concept in many ways, Realizeit provides multiple pieces of content and resources for each concept in the curriculum. The design is content agnostic--it is applicable in any learning domain and can deliver learning content in multiple formats.
The Evolution of Adaptive Analytics
In examining Realizeit learning analytics, UCF noticed in psychology rapid and early declines of student success based on the eight modules of the course. Non-success could be accurately predicted from the first to the second module. Thereafter, CTU noticed a similar trend in their courses. UCF discovered excessive variability in the non-success group, identifying four distinct profiles: Late momentum loss, early momentum loss, steady decline and flat line behavior. When CTU examined their data that found similar trends that were particularly critical because their courses were five weeks long. This led the Realizeit research unit to produce an animated portrayal of students moving though adaptive courses comparing their pace with course activities completed. Metaphorical student prototypes were named: Rabbits, Turtles, Frogs and Hares because of the styles by which they traversed their assignments. This animation will be shown in the session.
Next, the two universities, working with Realizeit, turned their attention to college algebra--UCF working with an external grading protocol and CTU functioning completely within Realizeit. Both institutions used metrics produced by the platform. In any analytics work it is truism that that best predictor of success is grade point average. UCF using GPA as a moderator viable and monitoring student revision strategies and effective use of time was able to increase the odds of success in college algebra from 3 to 1 against students in the first GPA quartile for to considerably better than 50%. The Realizeit research unit working with similar data for the CTU algebra course and using a time series approach found predictions similar to those at UCF, however the predictive power of those variables changed over time.
For session interaction, polling will determine participants’ use of adaptive learning. Session notes will be transcribed into a Google Doc for shared interaction after the conference, allowing context-specific issues to be discussed. Resources will be shared by presenters to help facilitate future participant research.
Both CTU and UCF, working with Realizeit have identified functional predictive analytics solutions within the context of adaptive learning. Interestingly, the UCF and CTU models work best for potentially low preforming students and not nearly as well for students with higher potential. In this session, we will discuss the methods behind our research and also the implications of these findings for improving course design to predicting students at risk and address student success using adaptive learning analytics.