Learning Analytics, Educational Data Mining, Adaptive Learning

At South Mountain Community College, a homegrown Learner Support System gathers data on students' usage of campus resources, streamlining the tutoring process and improving outcomes.

As an educational technologist, I seem always infatuated with the latest tools, even as I grow increasingly alert to what is lost as well as what is gained from their use.

Amid concerns about the growing use – and abuse – of quantitative measures in universities, a major new review examines the role of metrics in the assessment of research, from the REF to performance management

At the heart of great classroom instruction is the teacher’s ability to identify individual student needs and adjust instruction and intervention accordingly. However, a recent survey by Lexia Learning®, a Rosetta Stone® (NYSE:RST) company, suggests that significant gaps exist in teachers’ abilities to quickly access, interpret and act upon student data to support instruction. The survey, which polled more than 200 educators at the International Society for Technology in Education 2015 Conference and Expo (ISTE), indicated there is a growing need to have assessments more quickly pinpoint skill deficiencies while rapidly providing teachers with connections to actionable data for immediate instructional planning.

According to the survey, only 35 percent of the survey respondents felt that teachers at their schools had a high or very high level of comfort connecting data to instruction. The low figure suggests that the majority of teachers still have trouble using data to identify students’ problem areas and adjust instruction accordingly. When teachers are unable to make that correlation, students are unlikely to receive the appropriate level or intensity of instruction needed to drive academic success.

Setting out the responsibilities of educational institutions to ensure that learning analytics is carried out responsibly, appropriately and effectively.

One of the goals of academic assessment is to identify which students need help; the sooner they can be identified, the better. The promise of technology has been that its ability to collect unique data could make this process timelier, more accurate, and less burdensome.
But how might technolo

Thu, Jul 16, 2015 10:00 AM - 11:00 AM WST

Following on from our last webinar on Sharing our TinCan/xAPI@Work Journey, we give an update on creating a working proof of concept for TinCan/xAPI. Dr Kirsty Kitto will presents on the work being done in developing a toolkit, which uses xAPI to store data about student participation in learning activities designed using standard social media tools such as Facebook etc.

We discuss:

- What is status of adoption of TinCan/xAPI in the industry ? How fast or slowly is it moving now ?
- What can you realistically achieve now with xAPI ? What is the road map you need to take ?
- Are there opportunities for the corporate and education sectors to collaborate to increase adoption ?

Personalized and adaptive learning has been described as the so-called holy grail of education. The idea is not new, though its technological instantiation is getting increased attention. In a well-funded education system, personalized instruction happens when guided by a teacher as each students strengths and weaknesses and knowledge gaps are known. However, when classrooms start to exceed 20+ students, some type of mediating agent is needed in order to address knowledge gaps as it becomes impossible for a teacher to be aware of what is happening with each learner. So, while the human educator is the original (and best) personalized learning system, the current funding constraints and other resource challenges have raised the need for alternative approaches to make sure that each learner is receiving support reflective of her needs.

Key findings of the report include:

*  Nearly 70 percent of respondents at most educational levels reported that technology to report, manage and collect student data has increased in the last two years;
*  The most common use of data at all levels reported by respondents was to track student performance, ranging from 75-81 percent and the second most commonly reported use, from 70-72 percent, was to improve instruction;
*  The least common use of student data, according to respondents, was in support of research to improve instruction or curriculum;
K-12 and higher ed respondents also agreed that increased training in data systems use is the most effective way to support the increased use of individual student data, though K-12 survey takers were more likely to say so, at just above 60 percent, than their higher ed peers, at about 50 percent; and
*  Respondents at all levels appear fairly comfortable with current data security, with only 23 percent or less saying that data security or privacy need to be improved to make better use of the information.

Automated learning pathways are currently a hot topic in discussions on education because those pathways have the potential to personalize learning and provide timely intervention for students. With automated pathways, also known as adaptive learning, the instruction changes based on the students’ current levels of understanding. In some cases, adaptive learning is teacher-directed. In this case, teachers push new content to their students based on the learners’ previous performances. In other cases, the pathways are “system-generated” so the technology “automatically” adapts to meet the needs of individual students. The latter option is far more controversial because it elicits this question: Are algorithms replacing teachers? What if the system “misunderstands” and doesn’t provide students with the proper support and intervention?1