In this article we continue our discussion of how to get started with Open Learning Analytics by discussing the role that Student Success Plan (SSP) can play in Open Learning Analytics as the action component of the Learning Analytics Diamond. You can catch up on earlier articles in our Getting Started With Open Analytics series here.
Institutions continue to call for ways to improve the success rate for their student population. As increasing academic and personal demands present obstacles to a student's successful outcome, institutions have sought ways to help manage a clear academic pathway, positively impacting student success. SSP allows counseling services, student services, and student support to guide a student to their educational career success.
SSP is designed to improve retention, academic performance, persistence, and graduation rates. As an open source solution, SSP is a case management software system for managing coaching and counseling workflows. It provides solutions for identification of at-risk individuals and other students in need, allowing coaches or advisors to proactively intervene thus providing guidance, support, and monitoring for at-risk students. Historically, SSP has been used to monitor every targeted population of students, from athletes to part-time and returning students, from working students to new freshmen.
The heart of the SSP system is the management of Early Alerts. These are typically manually entered by an instructor regarding a students behavior that appears to be negatively impacting the student's success. Missed assignments, tardiness, and poor performance are clear examples where an instructor might enter an Early Alert to be routed to the student's case manager, enabling them to intervene with appropriate suggestions based on the behavior. Anecdotal evidence may suggest that a student should join a study group to increase their likelihood of success and the advisor can then make that recommendation and track the student with SSP.
While research has shown that the use of SSP is successful with outcomes (see 1. STUDENT SUCCESS PLAN: CONSTRUCTING AN EVIDENCE-BASED STUDENT SUPPORT SYSTEM THAT PROMOTES COLLEGE COMPLETION), alerts and intervention are based on anecdotal and manual intervention. Human interaction by an instructor to manually enter an early alert for a student potentially allows for some students to be missed and or misdiagnosed. Automation with proper analytics may be more comprehensive.
As the industry continues to develop new standards for data collection, learning activities are becoming increasingly more valuable in this space. IMS Global has stated that one of their key strategies going forward, is 2. "Making instrumentation / measurement of learning activities easy to enable collection of analytics – big and small data." With the increasing use of industry specifications such as xAPI and the recently released IMS Global specification Caliper, mass collection of learning activities has become far easier. Not only can the LMS send learning activities to a Learning Record Store, but so too can social media and other sources if so desired. These learning activities can paint a reasonable picture of a student's likelihood of success. Moreover, it's possible that an analytics engine can identify at-risk students based on all of their collected learning activity by removing or supplementing the anecdotal or human observations mentioned above.
The marriage of analysis and action represents two crucial points in the Learning Analytics Diamond. With a solid success rate as an intervention tool, SSP is poised to quickly make use of alert automation from an analytics engine. Work has begun on adding external APIs to automate the creation of Early Alerts from an external system such as the Apereo Learning Analytics Processor. Soon, SSP will be able to present accurate, automated Early Alerts to the advisors to take action on.
The marriage of the open sourced SSP, enabling counselors to guide students to improve their academic skills, with accurate and automated alerting from an analytics engine is an exciting addition to the space. At first, we will see analytics that help a student in a single course, but it's likely that analytics can be produced to improve a student's overall, holistic success in their academic program as well. As Open Learning Analytics moves forward, SSP will be part of steady march toward accurate intervention, improved monitoring, and improved student outcomes.