A persistent challenge for the learning analytics community is how to achieve a meaningful impact on educational practice. This paper proposes that Porter’s Value Chain framework provides a useful lens for addressing this challenge. This study developed operational definitions of a Learning Analytics Value Chain and mapped learning analytics research output (3,720 publications) over the last 16 years to its five stages: 1. Concept Development, 2. Prototyping & Efficacy, 3. Evaluation, 4. Dissemination, and 5. Impact & Iteration.

In this study, we present an approach to utilizing variance in students’ performance across different formats (multiple-choice, numeric input, word problems) as a target for personalization. We have developed a measure called challenge variance, that indicates the degree to which different formats pose varying levels of challenge for individual learners. We investigated whether challenge variance could be a useful source of information for developing learner models by analyzing data from an online math tutoring platform. Results demonstrated that challenge variance has a relationship with an external activity, indicating its utility as a means of predicting how well a learner will perform in a new setting. We discuss the affordances and issues with the measure and whether or not it could be a useful additional tool in developing personalized learner models as an intuitive and platform-agnostic measure of performance.

Given the growth in interest in human-centeredness within the learning analytics community - a workshop at LAK, a special issue in the Journal of Learning Analytics and multiple papers published on the topic - it seems an appropriate time to critically evaluate the popular design approach. Using a corpus of 165 publications that have substantial reference to both learning analytics and human-centeredness, the following paper delineates what is meant by "human-centered" and then discusses what the implications are for this approach. The conclusion reached through this analysis is that when authors refer to human-centeredness in learning analytics they are largely referring to stakeholder inclusion and the means by which this can be achieved (methodologically, politically and logistically). Furthermore, the justification for stakeholder inclusion is often coached in terms of its ability to develop more effective learning analytics applications along several dimensions (efficiency, efficacy, impact). With reference to human-centered design in other fields a discussion follows of the issues with such an approach and a prediction that LA will likely move toward a more neutral stance on stakeholder inclusion, as has occurred in both human-centered design and stakeholder engagement research in the past. A more stakeholder-neutral stance is defined as one in which stakeholder inclusion is one of many tools utilized in developing learning analytics applications.

This paper reports on a study aimed at identifying training requirements for both staff and students in higher education to enable more widespread use of learning analytics. Opinions of staff and students were captured through ten focus groups (37 students; 40 staff) and two surveys (1,390 students; 160 staff). Participants were predominantly from two higher education institutions in Ireland. Analysis of the results informed a framework for continuous professional development in learning analytics focusing on aspects of using data, legal and ethical considerations, policy, and workload. The framework presented here differentiates between the training needs of students, academic staff and professional services staff.

Until recently an assumption within the predictive modelling community has been that collecting more student data is always better. But in reaction to recent high profile data privacy scandals, many educators, scholars, students and administrators have been questioning the ethics of such a strategy. Suggestions are growing that the minimum amount of data should be collected to aid the function for which a prediction is being made. Yet, machine learning algorithms are primarily judged on metrics derived from prediction accuracy or whether they meet probabilistic criteria for significance. They are not routinely judged on whether they utilize the minimum number of the least sensitive features, preserving what we name here as data collection parsimony. We believe the ability to assess data collection parsimony would be a valuable addition to the suite of evaluations for any prediction strategy and to that end, the following paper provides an introduction to data collection parsimony, describes a novel method for quantifying the concept using empirical Bayes estimates and then tests the metric on real world data. Both theoretical and empirical benefits and limitations of this method are discussed. We conclude that for the purpose of model building this metric is superior to others in several ways, but there are some hurdles to effective implementation.

Involving teachers in the design of technology-enhanced learning environments is a useful method towards bridging the gap between research and practice. This is especially relevant for learning analytics tools, wherein the presentation of educational data to teachers or students requires meaningful sense-making to effectively support data-driven actions. In this paper, we present two case studies carried out in the context of two research projects in the USA and Spain which aimed to involve teachers in the co-design of learning analytics tools through professional development programs. The results of a cross-case analysis highlight lessons learned around challenges and principles regarding the meaningful involvement of teachers in learning analytics tooling design.

It is arguable that the chief aim of Learning Analytics is to use analytics for meaningful purposes in learning and teaching contexts, and that research in the field should advance this cause. However the field does not present a single clear understanding of what constitutes quality in Learning Analytics research.

In this paper we explore the potential role, value and utility of a personal code of ethics (COE) for learning analytics practitioners, and in particular we consider whether such a COE might usefully mediate individual actions and choices in relation to a more abstract institutional COE. While several institutional COEs now exist, little attention has been paid to detailing the ethical responsibilities of individual practitioners. To investigate the problems associated with developing and implementing a personal COE, we drafted an LA Practitioner COE based on other professional codes, and invited feedback from a range of learning analytics stakeholders and practitioners: ethicists, students, researchers and technology executives. Three main themes emerged from their reflections: 1. A need to balance real world demands with abstract principles, 2. The limits to individual accountability within the learning analytics space, and 3. The continuing value of debate around an aspirational code of ethics within the field of learning analytics.

Learning analytics is an interdisciplinary and inclusive field, a fact which makes the establishment of methodological norms both challenging and important. This community-building workshop intends to convene methodology-focused researchers to discuss new and established approaches, comment on the state of current practice, author pedagogical manuscripts, and co-develop guidelines to help move the field forward with quality and rigor.

The following paper is a proof-of-concept demonstration of a novel Bayesian framework for making inferences about individual students and the context in which they are learning. It has implications for both efforts to automate personalized instruction and to probabilistically model educational context. By modelling students as Bayesian learners, individuals who weigh their prior belief against current circumstantial data to reach conclusions, it becomes possible to both generate estimates of performance and the impact of the educational environment in probabilistic terms. This framework is tested through a Bayesian algorithm that can be used to characterize student prior knowledge in course material and predict student performance. This is demonstrated using both simulated data. The algorithm generates estimates that behave qualitatively as expected on simulated data and predict student performance substantially better than chance. A discussion of the results and the conceptual benefits of the framework follow.

Learning Analytics courses and degree programs both on-and offline have begun to proliferate over the last three years. As a result of this growth in interest from students, university administrators, researchers and instructors we believe it is a good time to review how these educational efforts are impacting the field, how synergy between instructors might be developed to greater serve the field and what kinds of best practices could be developed.