Learning Analytics, Educational Data Mining, Adaptive Learning

We sacrifice control in the name of convenience. As we become like cyborgs, we should expect more control over our technology. Tech has long aimed to provide additional conveniences for modern living, with the idea that a gadget would take care of something for us. The premise is that our lives are made easier when we worry less about the small stuff, stepping aside to allow technology do the grunt work. But the more we step aside, the less involved we are, and the less we control our environment, our information, our lives. We are giving algorithms control over increasingly complex aspects of our lives.

The idea of using an algorithm to care for humans has received popular attention recently with the case of a driver who died when his Tesla Model S drove underneath a semi that was crossing his lane. The car was in autopilot mode, with assistive radar and cameras activated; the driver died when the top of his car was sheared off by the underside of the semi trailer. Now begins the blame-aversion game that will become increasingly common as automation takes over automobiles: The car maker says autopilot is an assist feature and that the fault lies with the driver. Consumer Reports says the name “autopilot” suggests autonomy and that the fault lies with the software system. The driver — the one person directly affected by the incident — cannot share his take on things.

Although nudging in small doses makes a difference, nudging is no panacea for all of the complex problems found in higher education. There are few studies that evaluate the overall effectiveness of nudging in changing behaviors and sustaining impact.6 Some studies even note the adverse effects of nudging.7 Like anything else in life, knowing when to use nudging — and when enough is enough — can be a challenge.

The answer is not simple. Perhaps the deepest concern lies in the definition of the problem and in who decides the direction of nudges. Nudging can easily become shoving or smacking. Obviously, the intentions behind most higher education practices are pure, but with new technologies, we need to know more about the intentions and remain vigilant so that the resulting practices don’t become abusive. The unintended consequences of automating, depersonalizing, and behavioral exploitation are real. We must think critically about what is most important: the means or the end.

With the transformative nature of new capabilities, we should explore both the opportunities and the threats associated with nudging in higher education. This is especially true at a time when academic credentials beyond the high school diploma are needed to acquire entry-level jobs, when colleges and universities are experiencing retention challenges, and when funding for higher education is decreasing. Nudging, used wisely, offers a promising opportunity to redirect students’ decisions and to contribute to the success of those students facing the steepest barriers.

This article is drawn from the recent research by the EDUCAUSE Center for Analysis and Research (ECAR) and Gartner researchers on the state of analytics in higher education. This research explores the analytics trends as well as future predictions for the deployment of analytics technologies. Publications include The Analytics Landscape in Higher Education, 2015; Institutional Analytics in Higher Education; and Learning Analytics in Higher Education. More information about the analytics maturity index and deployment index can be found in the EDUCAUSE Core Data Service (participating) and the EDUCAUSE Benchmarking Service.

Analytics progress in higher education is moving slowly, at best. How can colleges and universities mature their analytics capabilities without working twice as hard?

News, voices and jobs for education professionals. Optimized for your mobile phone.

The college classroom has been impenetrable for those seeking to understand how students learn. This was more a function of the traditional methods of teaching and learning than a result of any intentional barriers. Student behaviors were fairly opaque—some note taking, possibly classroom discuss

No tutoring algorithm should be based purely on interaction data. The nuts and bolts of students’ learning experiences – from the lesson they are given through to the choice of knowledge representation – should be based on proven pedagogical principles. It is vital that these principles are baked into tutoring algorithms from the start, and that engineers work closely alongside pedagogical experts throughout the creation process.

Tutoring algorithms have a natural counterpart in real-time progress reports. It is the reports that are fed to parents and educators, who are ideally positioned to uncover the story behind each student’s data. They must be empowered to do exactly that.

An algorithmic approach is not sufficient to serve our students. Joshua has met with success because his teachers are active agents in his learning journey. His progress data may act as a guide, but it is Joshua’s teachers who can interpret his data within his unique context and take the relevant actions. For instance, the reports may highlight sporadic usage patterns (and give precise meaning to terms like ‘sporadic’) but the additional support that is needed for Joshua is a judgement best left to his school.

Algorithms and data need not be the mechanical vices of data scientists – with the right intentions, they can uplift educators and amplify their efforts to meet every the needs of every student. It is the combined potential of algorithms and human insight that will win the day.

Colleges and universities are doubling down on learning analytics. They’re trying to figure out how to better use the rich data they’re increasingly capturing about their students and how to improve our collective understanding of the impact of analytics on teaching and learning. At the Universit

CT covered the Hobsons announcement this past January, 2016, of its acquisition of the PAR (Predictive Analytics Reporting) Framework. Here, we talk with Ellen Wagner, Chief Research Officer for the PAR Framework and VP for Research at Hobsons to get a brief update on the current work of PAR after its first eight months with Hobsons.

Digital assessments have long been an effective means for freeing up instructors' time, particularly in blended learning settings, as well as for providing immediate formative feedback.17 Building on this work is the move to authentic assessment, to approaches in which humans and machines work in concert to quickly and accurately assess and provide feedback on student problems, where data is integrated from very diverse sources, and where data is collected longitudinally.18

With this shift we have, for the first time, data about virtually all aspects of students' skills, including the complex abilities that higher education attempts to foster—abilities that, in the modern economy, are more important than simple factual knowledge.19 We have the potential to assess postsecondary learners in ways that can improve depth, frequency, and response time, possibly expanding the scope with which students and instructors can monitor learning, including assessment of higher-level skills, and proving personalized feedback based on those assessments. However, the tools for understanding this data (e.g., edX ORA, Insights, EASE, and Discern) are still in their infancy. The grand challenge in data-intensive research and analysis in higher education is to find the means to extract such knowledge from the extremely rich data sets being generated today and to integrate these understandings into a coherent picture of our students, campuses, instructors, and curricular designs.

The grand challenge in data-intensive research and analysis in higher education is to find the means to extract knowledge from the extremely rich data sets being generated today and to distill this into usable information for students, instructors, and the public.

A specific type of adaptive learning technology, intelligent adaptive learning technology, is able to assess what students know and seeks to offer what they need to achieve content mastery. This technology “learns the learner” as the learner engages with it, which enables nuanced, personalized and relevant data collection and reporting that gives teachers insight into how the learner is solving problems and thinking.  In addition to tracking achievement, the technology identifies trends in student motivation and engagement so that teachers can optimize learning efficiency, learning tenacity and ultimately learning outcomes. While students are working through lessons, the technology analyzes every click, hesitation and answer in order to direct students based on what they need in the moment to ensure deep understanding of key concepts, develop fluency with important skills, and cultivate critical thinking.