Developing a Framework for the Effective Use of Learning Analytics

Research and experimentation is uncovering forms of best practice and possible factors on which to centre the analysis of students in an effective way, however learning analytics has yet to be comprehensively implemented country-wide in the United Kingdom. The chapter explores the current impact of learning analytics in higher education at mome discusses and observes the current vacancies with which a framework enabled to function with data visualisation could be utilised. The deliverable seeks to design an initial framework that has the potential to be utilised in a higher education setting for more effective and insightful decision making with regards to learner retention and engagement. This framework will combine the theory and scientific action of predictive analytics with a comparison of the most suitable data visualisation toolsets that are currently available in open-source software.

Post-Course Survey Development

Evaluating workplace training often involves using participant surveys to gather information about effectiveness. Unfortunately, how well these surveys are designed will play a major role in the information quality used to make conclusions. Following a proper survey design method will improve data quality and help trainers better understand what these data truly mean. Additionally, as a first step in a chain of evidence, properly designed post-course surveys will play a key role in connecting training with any on-the-job changes. This chapter will describe in detail a survey design process adapted from Spector (1992) to yield key insights about training's design, trainer and participants' interactions during training, and participants' perceived value of attending.

The Role of Learning Analytics in Global Higher Education

This chapter presents the role of learning analytics in global higher education, thus illustrating the theoretical and practical overview of learning analytics; learning analytics and educational data mining (EDM); learning analytics and learning management system (LMS); learning analytics and Course Signals; learning analytics and knowledge perspectives; learning analytics and social networking sites; and the significance of learning analytics in global higher education. The application of learning analytics is critical in global higher education that seeks to serve the school administrators and students, increase educational performance, sustain competitiveness, and fulfill expected accomplishment in global higher education. The chapter argues that applying learning analytics has the potential to improve educational performance and reach strategic goals in the information age.

Role of Learning Analytics in Enhancing Teaching and Learning

Data analytics, tools and techniques are no more confined to research organizations. These tools are being adopted by many organizations to generate business intelligence for improving decision making. Higher education institutions (HEIs) are beginning to use data analytics for improving their services and for increasing student grades and retention. Educational learning analytics are used to research and build models in several areas that can influence online learning systems. While use of analytics and data mining in education is increasing, sorting out fact from fiction and identifying research possibilities and practical applications are not easy. This chapter intends to help policymakers and administrators of HEIs understand how learning analytics have been used and can be applied for educational improvements.

Developing a Framework for the Visualisation of Learning Analytics in UK Higher Education

Learning analytics has vast potential as a tool to further unlock the effectiveness of education in a digital age. The amount of data that can be gathered from varying access points can provide new insight and knowledge into how learners are interacting with course materials, learning systems and even fellow classmates. Research and experimentation is uncovering forms of best practice and possible factors on which to centre the analysis of students in an effective way, however learning analytics has yet to be comprehensively implemented country-wide in the United Kingdom.

An Institution Wide Approach to Learning Analytics

The desire to provide personalized learning support for students has been a strong driver of the development of learning analytics capabilities at the University of Wollongong (UOW), Australia. A case study approach is taken to explore the diverse challenges faced when adopting an institution wide approach to learning analytics. Aspects explored include: establishing a clear strategy and governance, implementing foundation technology, developing and applying analytics and visualizations, managing organizational culture change, understanding student expectations, and addressing ethical challenges associated with learning analytics. This chapter draws upon the results of a UOW student survey conducted in late 2013 that explored first year student expectations regarding privacy in relation to learning analytics, and their preferred approach to interventions. Throughout it is noted that the academic endeavor, rather than technology and data management, drives the UOW adoption of learning analytics.

Here Be Dragons

Learning analytics is an emerging but rapidly growing field seen as offering unquestionable benefit to higher education institutions and students alike. Indeed, given its huge potential to transform the student experience, it could be argued that higher education has a duty to use learning analytics. In the flurry of excitement and eagerness to develop ever slicker predictive systems, few pause to consider whether the increasing use of student data also leads to increasing concerns. This chapter argues that the issue is not whether higher education should use student data, but under which conditions, for what purpose, for whose benefit, and in ways in which students may be actively involved. The authors explore issues including the constructs of general data and student data, and the scope for student responsibility in the collection, analysis and use of their data. An example of student engagement in practice reviews the policy created by the Open University in 2014. The chapter concludes with an exploration of general principles for a new deal on student data in learning analytics.

Advances in Algorithms for Re-Sampling Class-Imbalanced Educational Data Sets

Real world data sets often contain disproportionate sample sizes of observed groups making it difficult for predictive analytics algorithms. One of the many ways to combat inherent bias from class imbalance data is to perform re-sampling. In this book chapter we discuss popular re-sampling methods proposed in research literature, such as Synthetic Minority Over-sampling Technique (SMOTE) and Propensity Score Matching (PSM). We provide an insight into recent advances and our own novel algorithms under the umbrella term of Over-sampling Using Propensity Scores (OUPS). Using simulation we conduct experiments that result in statistical improvement in accuracy and sensitivity by using these new algorithmic approaches.

Personalising the Pathway

The Eynesbury Institute of Business and Technology (EIBT) is one of a growing number of private providers partnering with universities to establish pre-university pathway programs worldwide. As a second chance for prospective students who do not meet initial Australian Higher Education (HE) entrance requirements, pathway providers attract students early in their tertiary lifecycle to secure their destination. EIBT has an abundance of empirically-rich and ‘big' data that may be used to find pedagogically useful indicators, predictors and recommendations for teaching and learning advancement by careful evaluation of the findings. The work of ‘researchers' often resides in isolation from that of ‘educators', whereby the ‘gap' may reflect a poor-cycle of communication and interaction between empirical studies and praxis. This chapter is limited to a select and somewhat brief discussion of specific uses of Learning Analytics (LA) in the context of EIBT and related sense-making and predicting of student performance.

Outstanding Student Achievement

This chapter will describe, evidence and critically evaluate a pedagogical journey which takes the reader from a traditional position of the “academic as a domain expert” to what turns out to be a far more effective position as the “academic as a Learning to Learn expert”. The evidence used to confirm the value and effectiveness of this changed approach by the author over a period of 5 years or so is based on Learning Analytics which demonstrate significantly improved academic results and achievements. It also demonstrates that the author's teaching styles have a dramatic impact on the so-called BME Achievement Deficit, compared to many modules at the institution. It has also had a significant impact in terms of improving student satisfaction. The confirmatory evidence derived from the Learning Analytics is now being used to make informed choices by other colleagues to change their own pedagogical choices to also develop excellent achievement in their own modules and programmes