Personalized Learning Scenarios

Online consumer experiences provide strong evidence that computer scientists are developing methods to exploit user activity data and adapt accordingly. Consider the experience a consumer has when using a Movie app to choose a movie. Members can browse app offerings by category (e.g., Comedy) or search by a specific actor, director, or title. On choosing a movie, the member can see a brief description of it and compare its average rating by app users with that of other films in the same category. After watching a film, the member is asked to provide a simple rating of how much he or she enjoyed it. The next time the member returns to app, his or her browsing, watching, and rating activity data are used as a basis for recommending more films. The more a person uses app, the more app learns about his or her preferences and the more accurate the predicted enjoyment. But that is not all the data that are used. Because many other members are browsing, watching, and rating the same movies, the app recommendation algorithm is able to group members based on their activity data. Once members are matched, activities by some group members can be used to recommend movies to other group members. Such customization is not unique to Movie app, of course. Companies such as Amazon, Overstock, and Pandora keep track of users’ online activities and provide personalized recommendations in a similar way. 

Education is getting very close to a time when personalisation will become commonplace in learning. Imagine an introductory biology course. The instructor is responsible for supporting student learning, but her role has changed to one of designing, orchestrating, and supporting learning experiences rather than “telling.” Working within whatever parameters are set by the institution within which the course is offered, the instructor elaborates and communicates the course’s learning objectives and identifies resources and experiences through which those learning goals can be attained. Rather than requiring all students to listen to the same lectures and complete the same homework in the same sequence and at the same pace, the instructor points students toward a rich set of resources, some of which are online, and some of which are provided within classrooms and laboratories. Thus, students learn the required material by building and following their own learning maps. 

Suppose a student has reached a place where the next unit is population genetics. In an online learning system, the student’s dashboard shows a set of 20 different population genetics learning resources, including lectures by a master teacher, sophisticated video productions emphasizing visual images related to the genetics concepts, interactive population genetics simulation games, an online collaborative group project, and combinations of text and practice exercises. Each resource comes with a rating of how much of the population genetics portion of the learning map it covers, the size and range of learning gains attained by students who have used it in the past, and student ratings of the resource for ease and enjoyment of use. These ratings are derived from past activities of all students, such as “like” indicators, assessment results, and correlations between student activity and assessment results. 

The student chooses a resource to work with, and his or her interactions with it are used to continuously update the system’s model of how much he or she knows about population genetics. After the student has worked with the resource, the dashboard shows updated ratings for each population genetics learning resource; these ratings indicate how much of the unit content the student has not yet mastered is covered by each resource. At any time, the student may choose to take an online practice assessment for the population genetics unit. Student responses to this assessment give the system—and the student—an even better idea of what he or she has already mastered, how helpful different resources have been in achieving that mastery, and what still needs to be addressed. The teacher and the institution have access to the online learning data, which they can use to certify the student’s accomplishments. This scenario shows the possibility of leveraging data for improving student performance; another example of data use for “sensing” student learning and engagement is described in the sidebar on the moment of learning and illustrates how using detailed behavior data can pinpoint cognitive events. The increased ability to use data in these ways is due in part to developments in several fields of computer science and statistics. To support the understanding of what kinds of analyses are possible, the next section defines educational data mining, learning analytics, and visual data analytics, and describes the techniques they use to answer questions relevant to teaching and learning. 

                Capturing the Moment of Learning by Tracking Game Players’ Behaviors 

The Wheeling Jesuit University’s Cyber enabled Teaching and Learning through Game-based, Metaphor-Enhanced Learning Objects (CyGaMEs) project was successful in measuring learning using assessments embedded in games. CyGaMEs quantifies game play activity to track timed progress toward the game’s goal and uses this progress as a measure of player learning. CyGaMEs also captures a self-report on the game player’s engagement or flow, i.e., feelings of skill and challenge, as these feelings vary throughout the game play. In addition to timed progress and self-report of engagement, CyGaMEs captures behaviors the player uses during play. Reese et al. (in press) showed that this behavior data exposed a prototypical “moment of learning” that was confirmed by the timed progress report. Research using the flow data to determine how user experience interacts with learning is ongoing.