No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Towards a Cloud-Based Big Data Infrastructure for Higher Education Institutions: Emerging Technologies for Teaching and Learning
Abstract
This chapter reports about experiences gained in developing a learning analytics infrastructure for an ecosystem of different MOOC providers in Europe. These efforts originated in the European project ECO that aimed to develop a single-entry portal for various MOOC providers by developing shared technologies for these providers and distributing these technologies to the individual MOOC platforms of the project partners. The chapter presents a big data infrastructure that is able to handle learning activities from various sources and shows how the work in ECO led to a standardised approach for capturing learning analytics data according to the xAPI specification and storing them into cloud-based big data storage. The chapter begins with a definition of big data in higher education and thereafter describes the practical experiences gained from developing the learning analytics infrastructure.
... Many factors related to IT infrastructure, such as its usability and complexity are taken into consideration. Various studies have been conducted before examining the opportunities and challenges [9,10]. Baig et al [11]examined the advantages, costs, security, and risk aspects of adopting Big Data technology. ...
The importance of data to help the management of educational institutions in decision making is recognized by all parties to improve the quality and competitiveness of their alumnus in society. However, to process aBig Data, facilities and resource capabilities are needed to convert the data into information that can be easily visualized and consumed by various interested parties. As the inefficiency of the old technology use in helping the businesses’ needs, the infrastructure of the big data is important. Big data presents various challenges in infrastructure provision and resource constraints as well as privacy and security concerns. This paper provides an initial development of how to build Big Data infrastructure in an educational institution that is adaptable to existing conditions which provide considerable performance and capabilities to perform information mining to assist in decision making. The scenarios, in this case, provide valuable additional insights for organizations to apply to their environment and can be leveraged to reach critical decision making through data visualization.
... Learning analytics, AI in education and educational data mining recognise various standards in capturing data, with xAPI and SCORM being among the most prominent ones (Buckingham Shum and Luckin, 2019;Constapel et al., 2019). However, similar to the infrastructure proposed by Ruiz-Calleja et al. (2019) we anticipate these systems to operate as a service in the cloud to provide ubiquitous and scalable (Ternier et al., 2018;Zulkernine et al., 2013) support for workplace learning and potentially serve disparate networks and communities (Delen and Demirkan, 2013) that can benefit from employing these analytical services in their own workplace contexts. For example, Oracle cloud infrastructure allowed for rapid design of a novel COVID-19 vaccine candidate [3]. ...
Purpose
To help workers make the right decision, over the years, technological solutions and workplace learning analytics systems have been designed to aid this process (Ruiz-Calleja et al. , 2019). Recent developments in artificial intelligence (AI) have the potential to further revolutionise the integration of human and artificial learning and will impact human and machine collaboration during team work (Seeber et al. , 2020).
Design/methodology/approach
Complex problem-solving has been identified as one of the key skills for the future workforce (Hager and Beckett, 2019). Problems faced by today's workforce emerge in situ and everyday workplace learning is seen as an effective way to develop the skills and experience workers need to embrace these problems (Campbell, 2005; Jonassen et al. , 2006).
Findings
In this commentary the authors argue that the increased digitization of work and social interaction, combined with recent research on workplace learning analytics and AI opens up the possibility for designing automated real-time feedback systems capable of just-in-time, just-in-place support during complex problem-solving at work. As such, these systems can support augmented learning and professional development in situ .
Originality/value
The commentary reflects on the benefits of automated real-time feedback systems and argues for the need of shared research agenda to cohere research in the direction of AI-enabled workplace analytics and real-time feedback to support learning and development in the workplace.
From a psychometric point of view, assessment means to infer what a learner knows and can do in the real world from limited evidence observed in a standardized testing situation. From a learning analytics perspective assessment means to observe real behavior in digital learning environments to conclude the learner status with the intent to positively influence the learning process. Although psychometrics and learning analytics share similar goals, for instance, formative assessment, while applying different methods and theories, the two disciplines are so far highly separated. This chapter aims at paving the way for an advanced understanding of assessment by comparing and integrating the learning analytics and the psychometric approach of assessment. We will discuss means to show this new way of assessment of educational concepts such as (meta-) cognition, motivation, and reading comprehension skills that can be addressed either from data-driven approach (learning analytics) or from a theory-driven approach (psychometrics). Finally, we show that radically new ways of assessment are located in the middle space where both disciplines are combined into a new research discipline called ‘Computational Psychometrics’.
While learning analytics (LA) is maturing from being a trend to being part of the institutional toolbox, the need for more empirical evidences about the effects for LA on the actual stakeholders, i.e. learners and teachers, is increasing. Within this paper we report about a further evaluation iteration of the Evaluation Framework for Learning Analytics (EFLA) that provides an efficient and effective measure to get insights into the application of LA in educational institutes. For this empirical study we have thus developed and implemented several LA widgets into a MOOC platform’s dashboard and evaluated these widgets using the EFLA as well as the framework itself using principal component and reliability analysis. The results show that the EFLA is able to measure differences between widget versions. Furthermore, they indicate that the framework is highly reliable after slightly adapting its dimensions.
It has been long argued that learning analytics has the potential to act as a \middle space" between the learning sciences and data analytics, creating technical possibilities for exploring the vast amount of data generated in online learning environments. One common learning analytics intervention is the learning dashboard, a support tool for teachers and learners alike that allows them to gain insight into the learning process. Although several related works have scrutinised the state-of-the-art in the field of learning dashboards, none have addressed the theoretical foundation that should inform the design of such interventions. In this systematic literature review, we analyse the extent to which theories and models from learning sciences have been integrated into the development of learning dashboards aimed at learners. Our critical examination reveals the most common educational concepts and the context in which they have been applied. We find evidence that current designs foster competition between learners rather than knowledge mastery, offering misguided frames of reference for comparison.
Learning Pulse explores whether using a machine learning approach on multimodal data such as heart rate, step count, weather condition and learning activity can be used to predict learning performance in self-regulated learning settings. An experiment was carried out lasting eight weeks involving PhD students as participants, each of them wearing a Fitbit HR wristband and having their application on their computer recorded during their learning and working activities throughout the day. A software infrastructure for collecting multimodal learning experiences was implemented. As part of this infrastructure a Data Processing Application was developed to pre-process, analyse and generate predictions to provide feedback to the users about their learning performance. Data from different sources were stored using the xAPI standard into a cloud-based Learning Record Store. The participants of the experiment were asked to rate their learning experience through an Activity Rating Tool indicating their perceived level of productivity, stress, challenge and abilities. These self-reported performance indicators were used as markers to train a Linear Mixed Effect Model to generate learner-specific predictions of the learning performance. We discuss the advantages and the limitations of the used approach, highlighting further development points.
Most current MOOC models basically follow a trend originated at the top US universities that is broadly identified in the literature as xMOOCs. These models are proving to be inconsistent with the European standards for formal higher education due to their low-level of learner support and lack of an enriched pedagogical approach. Within the framework of the EU-funded project Elearning, Communication and Open-data: Massive Mobile, Ubiquitous and Open Learning (ECO) a research team from a pool of institutions with experience in MOOC design conceived a model that attempts to meet the above-referred challenge. In this paper we present a description of the model and its most innovative features, its theoretical foundations and context of development, as well as scenarios of implementation.
The widespread adoption of Learning Analytics (LA) and Educational Data Mining (EDM) has somewhat stagnated recently, and in some prominent cases even been reversed following concerns by governments, stakeholders and civil rights groups about privacy and ethics applied to the handling of personal data. In this ongoing discussion, fears and realities are often indistinguishably mixed up, leading to an atmosphere of uncertainty among potential beneficiaries of Learning Analytics, as well as hesitations among institutional managers who aim to innovate their institution's learning support by implementing data and analytics with a view on improving student success. In this paper, we try to get to the heart of the matter, by analysing the most common views and the propositions made by the LA community to solve them. We conclude the paper with an eight-point checklist named DELICATE that can be applied by researchers, policy makers and institutional managers to facilitate a trusted implementation of Learning Analytics.
We present a Connected Learning Analytics (CLA) toolkit, which enables data to be extracted from social media and imported into a Learning Record Store (LRS), as defined by the new xAPI standard. A number of implementation issues are discussed, and a mapping that will enable the consistent storage and then analysis of xAPI verb/object/activity statements across different social media and online environments is introduced. A set of example learning activities are proposed, each facilitated by the Learning Analytics beyond the LMS that the toolkit enables.
This paper describes the research and development of tangible interactive ambient display prototypes to support learning scenarios. Therefore a prototypical system design called the Feedback Cube is presented. The prototypes combine motion sensors, visual and auditive actuators, as well as wireless communication capabilities in a cubic layout. An initial formative study underpins the prototypes' potential to facilitate interaction and/or indicate feedback. Based on the presented results possible applications scenarios in a learning context are outlined.
Constructionism can be a powerful framework for teaching
complex content to novices. At the core of constructionism is the suggestion that by enabling learners to build creative artifacts that require complex content to function, those learners will have opportunities to learn this content in contextualized, personally meaningful ways. In this paper, we investigate the relevance of a set of approaches broadly called “educational data mining” or “learning analytics” (henceforth, EDM) to help provide a basis for quantitative research on constructionist learning which does not abandon the richness seen as essential by many researchers in that paradigm. We suggest that EDM may have the potential to support research that is meaningful and useful both to researchers working actively in the constructionist tradition but also to wider communities. Finally, we explore potential collaborations between researchers in the EDM and constructionist traditions; such collaborations have the potential to enhance the ability of constructionist researchers to make rich inferences about learning and learners, while providing EDM researchers with many interesting new research questions and challenges.
With the increase in available educational data, it is expected that Learning Analytics will become a powerful means to inform and support learners, teachers and their institutions in better understanding and predicting personal learning needs and performance. However, the processes and requirements behind the beneficial application of Learning and Knowledge Analytics as well as the consequences for learning and teaching are still far from being understood. In this paper, we explore the key dimensions of Learning Analytics (LA), the critical problem zones, and some potential dangers to the beneficial exploitation of educational data. We propose and discuss a generic design framework that can act as a useful guide for setting up Learning Analytics services in support of educational practice and learner guidance, in quality assurance, curriculum development, and in improving teacher effectiveness and efficiency. Furthermore, the presented article intends to inform about soft barriers and limitations of Learning Analytics. We identify the required skills and competences that make meaningful use of Learning Analytics data possible to overcome gaps in interpretation literacy among educational stakeholders. We also discuss privacy and ethical issues and suggest ways in which these issues can be addressed through policy guidelines and best practice examples.
Drachsler, H., Bogers, T., Vuorikari, R., Verbert, K., Duval, E., Manouselis, N., Beham, G., Lindstaedt, S., Stern, H., Friedrich, M., & Wolpers, M. (2010). Issues and considerations regarding sharable data sets for recommender systems in technology enhanced learning. In N. Manouselis, H. Drachsler, K. Verbert, & O. Santos (Eds.), Elsevier Procedia Computer Science: Volume 1, Issue 2. Proceedings of the 1st Workshop on Recommender Systems for Technology Enhanced Learning (RecSysTEL 2010) (pp. 2849-2858). doi: 10.1016/j.procs.2010.08.010.
In order to capture current educational practices in eLearning courses, more advanced learning design capabilities are needed than are provided by the open eLearning specifications hitherto available. Specifically, these fall short in terms of multi-role workflows, collaborative peer-interaction, personalization and support for learning services. We present a new specification that both extends and integrates current specifications to support the portable representation of units of learning (e.g. lessons, learning events) that have advanced learning designs. This is the Learning Design specification. It enables the creation of a complete, abstract and portable description of the pedagogical approach taken in a course, which can then be realized by a conforming system. It can model multi-role teaching-learning processes and supports personalization of learning routes. The underlying generic pedagogical modelling language has been translated into a specification (a standard developed and agreed upon by domain and industry experts) that was developed in the context of IMS, one of the major bodies involved in the development of interoperability specifications in the field of eLearning. The IMS Learning Design specification is discussed in this article in the context of its current status, its limitations and its future development.
Collaborative learning is considered a critical 21st century skill. Much is known about its contribution to learning, but still investigating a process of collaboration remains a challenge. This paper approaches the investigation on collaborative learning from a psychophysiological perspective. An experiment was set up to explore whether biosensors can play a role in analysing collaborative learning. On the one hand, we identified five physiological coupling indices (PCIs) found in the literature: 1) Signal Matching (SM), 2) Instantaneous Derivative Matching (IDM), 3) Directional Agreement (DA), 4) Pearson's correlation coefficient (PCC) and the 5) Fisher's z-transform (FZT) of the PCC. On the other hand, three collaborative learning measurements were used: 1) collaborative will (CW), 2) collaborative learning product (CLP) and 3) dual learning gain (DLG). Regression analyses showed that out of the five PCIs, IDM related the most to CW and was the best predictor of the CLP. Meanwhile, DA predicted DLG the best. These results play a role in determining informative collaboration measures for designing a learning analytics, biofeedback dashboard.
The article deals with the interplay between learning analytics and massive open online courses (MOOCs) and provides a conceptual framework to situate ongoing research in the MOOC and learning analytics innovation cycle (MOLAC framework). The MOLAC framework is organized on three levels: On the micro-level, the data collection and analytics activities are focused on individual reflection and individual prediction. On the meso-level, data from several open courses are combined to support benchmarking and to create insights about behaviour of groups of learners rather than the individual. These insights can inform the institution to adapt their educational model. On the macro-level of the framework, cross-institutional learning analytics enables to develop learning and teaching interventions that can be tested in a cluster of educational organizations to analyse the impact of these interventions beyond contextual factors. The article proposes four areas of future activities that are needed to enable the MOLAC framework. These are the standardization of the description of the educational design of MOOCs, data sharing facilities across institutions, joint policymaking and ethical guidelines and last but not least standardized evaluation approaches.
This article introduces learning analytics dashboards that visualize learning traces for learners and teachers. We present a conceptual framework that helps to analyze learning analytics applications for these kinds of users. We then present our own work in this area and compare with 15 related dashboard applications for learning. Most evaluations evaluate only part of our conceptual framework and do not assess whether dashboards contribute to behavior change or new understanding, probably also because such assessment requires longitudinal studies.
From the Publisher:
A groundbreaking addition to the existing literature, Exploratory Data Mining and Data Cleaning serves as an important reference for data analysts who need to analyze large amounts of unfamiliar data, operations managers, and students in undergraduate or graduate-level courses, dealing with data analysis and data mining.
In this paper we present our design and implementation of a SCORM (Sharable Content Object Reference Model)- conformant CS courseware based on the latest SCORM specification 1.2, released by ADL (Advanced Distributed Learning) on Oct. 1, 2001. All learning resources contained in an existing Java course are re-designed according to the SCORM Content Model and further described with corresponding Assets-, SCO-, and Content Aggregation metadata. Also the course structure is reconstructed based on the SCORM Content Packaging specification, which provides a standardized way to represent the aggregation of learning resources and further exchange them between different learning management systems. Moreover, a Web-based SCORM Run-Time Environment is implemented utilizing Java Server Pages, Java Servlet, and JavaScript, which is able to dynamically render the course structure into its Web presentation on the basis of pre-defined SCORM Content Packaging Application Profile. Our SCORM-conformant development actually constitutes an early exploration to the great potential of the SCORM specification.