Ángel Hernández-García

Can we predict success from log data in VLEs? Classification of interactions for learning analytics and their relation with performance in VLE-supported F2F and online learning

Learning analytics is the analysis of electronic learning data which allows teachers, course designers and administrators of virtual learning environments to search for unobserved patterns and underlying information in learning processes. The main aim of learning analytics is to improve learning outcomes and the overall learning process in electronic learning virtual classrooms and computer-supported education. The most basic unit of learning data in virtual learning environments for learning analytics is the interaction, but there is no consensus yet on which interactions are relevant for effective learning. Drawing upon extant literature, this research defines three system-independent classifications of interactions and evaluates the relation of their components with academic performance across two different learning modalities: virtual learning environment (VLE) supported face-to-face (F2F) and online learning. In order to do so, we performed an empirical study with data from six online and two VLE-supported F2F courses. Data extraction and analysis required the development of an ad hoc tool based on the proposed interaction classification. The main finding from this research is that, for each classification, there is a relation between some type of interactions and academic performance in online courses, whereas this relation is non-significant in the case of VLE-supported F2F courses. Implications for theory and practice are discussed next.

Behavioral intention, use behavior and the acceptance of electronic learning systems: Differences between higher education and lifelong learning

Abstract Widespread implementation of e-learning systems – learning management systems, virtual learning environments – across higher education institutions has aroused great interest on the study of e-learning acceptance. Acceptance studies focus on the predictors of system adoption and use, with behavioral intention to use the system as a proxy for actual use. This study proposes a TAM3-based model – with the inclusion of two additional variables: personal innovativeness in the domain of information technology and perceived interaction – to study the factors influencing the acceptance of e-learning systems. Attention is also brought towards the role of behavioral intention, especially in its relation with use behavior. In order to do so, two different settings were considered: higher education and lifelong learning; data was gathered from a survey administrated to Spanish graduate and lifelong learning students, and partial least squares analysis was used to test the research model. Results supported TAM relations, except for the intention-behavior linkage, and unveiled a dual nature of perceived usefulness – with one component related to efficiency and performance, and another component related to flexibility. The adequacy of applying TAM3-based models in educational contexts and suitability of actual system usage measures are also discussed.

Tap into visual analysis of customization of grouping of activities in eLearning

We have implemented a tool to study relationships and patterns.Temporal correlation of the grouping of activities and students grades was studied.The tool searches for patterns in the frequencies of grouping activities and/or student grades.There is a pattern in the students behavior and performance.The results are consistent across different courses. The use of electronic media in education has a strong impact of on student performance. Prior research has investigated the impact of forum reading and posting, as well as access to reading resources, on academic performance. However, little is known about the relationship between the temporal frequency of these activities and individual students performance. In addition, some studies have proposed different categorizations of student activities, and proved the usefulness of these characterizations for predictive purposes and better understanding of the learning process. One of the biggest concerns when teaching courses in a virtual learning environment is to create and develop instruction in a way that it improves the overall learning experience and results. The present study addresses this concern by drawing upon factors influencing academic performance; more specifically, the study focuses on objective factors related to the interaction between the student and the system (number of resources visited in the learning platform, and number of forum posts and views). On top of that, a visualization tool was designed and implemented to allow for further investigation of the relevance of the study variables. The results from the study show that there is a recurrent pattern in the frequency of behaviors and performance across different courses.

Barriers and drivers for non-shoppers in B2C e-commerce: A latent class exploratory analysis

The barriers and drivers of e-shopping, as well as segmentation and behavior of e-shoppers, have been long studied in the last two decades, but the behavior of non-shoppers in business-to-consumer (B2C) e-commerce is still an open field for research which has seldom been dealt with. Our exploratory study has as its main objective the classification of non-shoppers in B2C e-commerce based on the barriers which keep deterring them from purchasing on the Internet and the drivers which might lead them to engage in e-shopping. In order to achieve this goal, data was gathered from 1499 Spanish respondents from a nationwide household panel survey. The responses were analyzed using a latent class analysis (LCA) approach and the results show four different types of non-shoppers based on the barriers for online shopping, while six different groups were identified based on the drivers to start shopping on the Internet. Implications for research and practice from the findings of the study are discussed in the final section.

Learning services-based technological ecosystems

The gap between technology and learning methods has two important implications: on the one hand, we should not expect the integration of technological advances into teaching to be an easy task; and there is a danger that mature educational technologies and methods might not give an adequate answer to the demands and needs of society, underusing their transforming potential to improve learning processes. This study discusses the need for a new technological environment supporting learning services, and proposes the concept of the technological learning ecosystem as a solution to both problems. Educational ecosystems should be able to break the technological constraints of existing learning platforms and achieve an effective improvement in learning processes. Our proposed educational ecosystems pivot around five specific lines of action: 1) a framework architecture that supports learning service-based ecosystems; 2) learning analytics for educational decision making; 3) adaptive knowledge systems; 4) gamification of learning processes; 5) semantic portfolios to collect evidence of learning.

Exploring Student Interactions: Learning Analytics Tools for Student Tracking

This paper presents four categories of learning analytics tools: dashboards, ad hoc tools, tools for analysis of specific issues, and learning analytics frameworks, and details the characteristics of a selection of tools within each category: (1) Moodle Dashboard and Moodle default reporting tool; (2) Interactions and Teamwork Assessment Tool; (3) SNAPP, GraphFES and Moodle Engagement Analytics; and (4) VeLA and GISMO. The study investigates how these tools can be applied to the analysis of courses by using real data from a course that made intensive use of forums, wikis, web resources, videos, quizzes and assignments. The discussion that follows points out how the different tools complement each other, and suggests the implementation of basic dashboards in learning platforms and the use of external frameworks for learning analytics.

Analysis and Improvement of Knowledge Management Processes in Organizations Using the Business Process Model Notation

Successful knowledge management is one of the main challenges for any kind of organization. This paper aims to enhance knowledge management processes within companies and institutions, by analyzing different processes that are part of common stages along all knowledge management lifecycles described in the literature. The processes have been modeled using the Business Process Model and Notation with a high abstraction level, in order to cover a wide range of organizations. The paper also presents a possible evolution and enhancement of knowledge management processes using the Business Process Model and Notation diagrams, including the use of superior and better performing technological solutions to support knowledge management processes. As a result, we propose a set of improvements that can be extrapolated to other knowledge management-related business processes.

Evaluation of the CTMTC Methodology for Assessment of Teamwork Competence Development and Acquisition in Higher Education

The majority of tasks and processes at the workplace involve the collaboration of two or more people, which explains that teamwork competence acquisition has become a priority for educational institutions. In project-based learning, student assessment is complex and generally focuses on the final outcome delivered by the group, without paying attention to the contribution of each individual or to the complete process. CTMTC is a methodology that facilitates teamwork competence acquisition and individual and group assessment in collaborative learning. This study describes and evaluates the application of CTMTC for student assessment in group project-based learning in Higher Education. The study also shows a particular case scenario of application of CTMTC and evaluates the benefits derived from the use of CTMTC. The results suggest that the methodology should be tailored to students’ needs and course characteristics, and reveal a positive perception from students about the application of the CTMTC methodology.

Perceived Compatibility and the Adoption of B2C E-Commerce by Non-buyers

The purpose of this article is to study the factors which affect the intention to buy online for users who have never made any prior purchase using the electronic channel, with special focus to the role of perceived compatibility. To do so, an adoption model for e-commerce was proposed on the basis of the Technology Adoption Model (TAM) and the Innovations Diffusion Theory (IDT). In order to validate the model, data gathered amongst Spanish consumers who had no experience using e-commerce, were analyzed using the partial least squares (PLS) method. The results have demonstrated the importance of perceived compatibility as a significant factor to foster non-buyers’ adoption of electronic business-to-consumer e-commerce (eB2C).

Bridging the Gap between LMS and Social Network Learning Analytics in Online Learning

Despite the great potential of social network analysis SNA methods and visualizations for learning analytics in computer-supported collaborative learning CSCL, these approaches have not been fully explored due to two important barriers: the scarcity and limited functionality of built-in tools in Learning Management Systems LMS, and the difficulty to import educational data from formal virtual learning environments into social network analysis programs. This study aims to cover that gap by introducing GraphFES, an application and web service for extraction of interaction data from Moodle message boards and generation of the corresponding social graphs for later analysis using Gephi, a general purpose SNA software. In addition, this paper briefly illustrates the potential of the combination of the three systems Moodle, GraphFES and Gephi for social learning analytics using real data from a computer-supported collaborative learning course with strong focus on teamwork and intensive use of forums.