A Customizable and Incremental Processing Approach for Learning Analytics

Abstract

The ability of learning analytics to improve the learning/teaching processes is widely recognized. In this paper, the learning analytics architecture developed at the Digital Content Production Center of the Technical University of Cartagena (Spain) is presented. This architecture contributes to the field of learning analytics in two aspects: it allows for dashboard customization and improves the efficiency of the analysis of learners' interaction data. Events resulting from learners' interaction are captured and stored in Caliper standard format, to be further processed incrementally to allow dashboards to be shown without delay to teachers. Customization is considered a mandatory requirement for learning analytics tools, however, although some proposals have recently been made, a greater research effort in this topic is necessary. In the present work, this requirement is addressed by defining a domain-specific language (DSL) that allows teachers to customize dashboards. This language allows to express indicators (logical expressions) that classify students into different groups depending on their performance level. The paper also shows how our learning analytics approach was evaluated with a course that applies a flipped classroom method, and how it compares to the most relevant related works that have been published.

Goal-oriented student motivation in learning analytics: How can a requirements-driven approach help?

“…The Learning modeling is a crucial task in the emerging research area of LA, recently studies (e.g., Pérez-Berenguer & García-Molina 2019 ; 2020 ; Nouira et al, 2019 ; Costa et al, 2020 ) conducted by the LA community identify the needs in order to Leveraging the MDE paradigm (Schmidt, 2006 ) (e.g., meta-modeling, model transformation and code generation) to improve the learning process using the conceptualization and explanation in the context of learning analytic. In (Costa et al, 2020 ), ontology-driven conceptual modeling is adopted in coordinated way with Learning Analytics in purpose of academic performance monitoring, in which, the conceptual models are independent of underlying digital trace interactions (known as xAPI data).…”

A Dual-Network Modeling Architecture for Statistical Evaluation of College Graduates’ Working Ability in Consistence with Their Job Position and Remuneration

“…Machine learning frameworks have been used in data stream mining as the data information is small, weak, and discontinuous; for instance, naive Bayes and support vector machine techniques are successfully applied for document-level sentiment analysis after proper data preprocessing [19]. Dynamic big data analytical technique has been applied to investigate the ability relationships between programming and testing and thus to propose a customizable and incremental processing approach for learning analytics [20,21]. However, the connection analysis of the college in-school cultivation and the companies' ability requirement is much inevitable for selecting talents with core working competence.…”

Rendimiento De Futuros Maestros en Problemas Verbales De "Parte De"

“…En los últimos años han proliferado tanto en el ámbito de la Educación Superior como en otras etapas educativas (Infantil, Primaria, Secundaria, Bachillerato, Ciclos formativos) el uso de entornos tecnológicos de aprendizaje, tutores inteligentes o plataformas de aprendizaje asistido por ordenador (p.e. Moodle, Edmodo o Bakpax) que pueden utilizarse tanto en medios móviles como pantallas inteligentes y que permiten registrar las interacciones o trazas digitales de estudiante-computador, estudiante-profesor o estudiante-contenido (Calvet Liñan y Juan Pérez., 2015;Long et al, 2011;Pérez-Berenguer et al 2020;Romero et al, 2008) dando origen a la denominada Analítica de datos de aprendizaje ("Learning Analytics, LA").…”