Data mining and analytics technology can help colleges graduate more students, said Mark Milliron, co-founder of Civitas Learning, in a keynote speech at the Blended Learning Conference in Denver. But colleges need to get the right data to the right people in the right way, said Milliron, whose experience includes Western Governors University and the Gates Foundation.
The problem is actually getting student learning data to the front lines where faculty can use it to test innovations, create interventions and predict actions such as likelihood of course completion and graduation. Too often, colleges focus so much on accountability analytics that they hamstring their ability to get data to faculty.
If faculty, advisers and students have access to learning data, they can make more informed decisions.
Colleges are using technology in different ways to help students stay on track to finish their degree, writes Tanya Roscorla for the Center for Digital Education.
Austin Community College‘s Degree Map application shows students how they’re progressing toward a degree, which courses they need to take next and how costly it would be in time and money to switch degrees. It also predicts when students choose “toxic” course combinations with a high risk of failure.
At El Paso Community College, an app allows students to choose an academic goal, such as earning a 3.5 grade point average, and then track their progress toward meeting the goal.
University of Texas at Austin students created a Facebook app called hoot.me for large lecture classes. Students use the app to ask questions, which are answered by five or six high achievers known as “owls.” Professors can look at students’ questions to see what issues need to be addressed.
Colleges also are analyzing data to redesign courses, writes Roscorla. Colorado Community Colleges combined remedial reading and writing to streamline developmental requirements. Students who score the lowest on placement tests now receive extra academic support.
Data-mining is helping Rio Salado College predict online students’ likely success and failure, reports the Chronicle of Higher Education. The Arizona community college is a pioneer in online education.
By the eighth day of class, Rio Salado College predicts with 70-percent accuracy whether a student will score a C or better in a course.
That’s possible because a Web course can be like a classroom with a camera rigged over every desk. The learning software logs students’ moves, leaving a rich “clickstream” for data sleuths to manipulate.
Running the algorithms, officials found clusters of behaviors that helped predict success. Did a student log in to the course homepage? View the syllabus? Open an assessment? When did she turn in an assignment? How does his behavior compare with that of previous students?
Instructors can see at a glance who’s green (likely to complete the course with a C or better), yellow (at risk of not earning a C), and red (highly unlikely to earn a C). That makes it possible to offer extra help before it’s too late.
The college is trying to intervene before the lights turn yellow or red.
For example, early data showed students in general-education courses who log in on Day 1 of class succeed 21 percent more often than those who don’t. So Rio Salado blasted welcome e-mails to students the night before courses began, encouraging them to log in.
The next step is a widespread rollout of the color-coded alerts, one that will put the technology in the hands of many more professors and students. The hope, (physical sciences instructor Shannon) Corona says, is that a yellow signal might prompt students to say to themselves: “Gosh, I’m only spending five hours a week in this course. Obviously students who have taken this course before me and were successful were spending more time. So maybe I need to adjust my schedule.”
In the future, colleges may ask students for an array of personal data in order to customize courses to fit each student’s abilities, interests and personalities, says George Siemens, an analytics expert at Canada’s Athabasca University.
Personalized guidance for academic surfers is the goal of Sherpa, software developed by the South Orange County Community College District. Sherpa mines student data to guide them to relevant courses, information, and services, reports Chronicle of Higher Education.
A new student might get a link to the online orientation. A student with a high grade-point average might get a link to the honors program. A student with low grades might be pointed to tutoring services.
With more information about students, the suggestions could get much more specific. Jim Gaston, South Orange’s associate director for IT, academic systems, and special projects, gave the example of a tip he hopes to be able to send to a student who hasn’t yet registered for class:
“Your classes are filling fast. We looked at your academic plan and saw that you plan on transferring to UC Berkeley as a biology major. We searched the class schedule. We found a set of courses you said you were interested in. Based on the pattern of classes you’ve taken in the past, here are the four classes we think you’re going to be most interested in. We’ve already screened them for pre-recs. They don’t have a time conflict with when you said you were going to work. And one of them is your favorite instructor.”
Creepy? Not to a generation that’s used to intelligent recommendations from Amazon, Pandora, Facebook, iTunes, and Netflix.