2) improvement of learners’ social interactions; 3) improvement of learners’ self-regulated learning skills; and 4) prediction of learners’ behavior. However, there are also significant risks associated with data collection and processing, such as privacy, transparency, biases, misinterpretations, etc., which must also be taken into account, and require creating specialized units and training the personnel in data management.
KEYWORDS: Data-driven innovation, learning analytics, digital education
¿Qué puede hacer la innovación de la educación de la ingeniería para el estudiante y qué puede hacer el estudiante para la misma?
RESUMEN. La innovación en la educación, en general, y la innovación en la educación de ingeniería, en particular, deben estar respaldadas por datos, debidamente recopilados y analizados para guiar los procesos de toma de decisiones. Hoy es posible recopilar datos de muchos grupos de interés (no solo estudiantes), y también recopilar muchos más datos de cada interesado. Sin embargo, los datos de bajo nivel recopilados al monitorear las interacciones de los múltiples interesados con las plataformas de aprendizaje y otros sistemas informáticos deben transformarse en indicadores y visualizaciones de alto nivel que guíen los procesos de toma de decisiones. El objetivo de este documento es discutir algunas tendencias notables en la innovación basada en datos en la educación de ingeniería, que incluyen: 1) mejora del contenido educativo; 2) mejora de las interacciones sociales de los alumnos; 3) mejora de las habilidades de aprendizaje autorreguladas de los alumnos; y 4) predicción del comportamiento de los alumnos. Sin embargo, también existen riesgos significativos asociados con la recopilación y el procesamiento de datos, que incluyen privacidad, transparencia, sesgos, malas interpretaciones, etc., que también deben tenerse en cuenta y que requieren la creación de unidades especializadas y la capacitación del personal en la gestión de datos.
PALABRAS CLAVE: innovación basada en datos, análisis de aprendizaje, educación digital
1. INTRODUCTION
The rapid changes taking place in today’s world have important consequences for education in general, and for engineering education in particular. Traditional “chalk and talk” teaching methodologies are not effective in engineering education, where it is necessary to combine the explanation of complex concepts with the practice of these concepts in realistic scenarios. In order to do this, it is necessary to apply learner-centered methodologies that promote active learning (Alario-Hoyos, Estévez-Ayres, Delgado Kloos, Villena-Román, Muñoz-Merino, et al., 2019), and that can be tailored to different education contexts, including face-to-face education in the classroom, online education, and blended (or hybrid) education (Pérez-Sanagustín, Hilliger, Alario-Hoyos, Delgado Kloos, & Rayyan, 2017).
Innovation in engineering education cannot take place without the support of a multi-disciplinary team of specialized professionals. Instructional designers must advise teachers on how to redesign their traditional course to turn it into a blended learning experience, making the most of the available resources with the aim to promote active learning (Baepler, Walker, & Driessen, 2014). Pedagogues and psychologists must contribute with the understanding and development of self-regulated learning (SRL) skills to ensure student success, especially in engineering education where further development of SRL skills is required to succeed (Zimmerman, 2013). Developers must create applications and simulators to put into practice and evaluate the key concepts of each course. Researchers and data scientists must collect and analyze data, offering visualizations so that the main stakeholders of the educational process (students, teachers, managers, etc.) can make informed decisions. All in all, innovation in engineering education is a multidisciplinary effort in which all supporting professionals and actions must be aligned with the ultimate goal to benefit students.
Among the abovementioned professionals, the role of researchers and data scientists is becoming more and more important in the last few years. Over the course of time, many efforts to innovate in engineering education have been undertaken without considering the research advances in the field of technology-enhanced learning. Today, with the amount of data that can be collected for the particular context of each educational institution, there is no longer an excuse for not implementing data-driven decision-making processes at the different levels: 1) teachers must rely on data to improve their content and the methodologies used in their classes; 2) students must rely on data to detect their knowledge gaps and improve their SRL skills; and 3) managers must rely on data to detect unbalanced programs or unsatisfactory courses, and to offer personalized pathways for students.
The aim of this paper is to present and discuss some relevant trends in data-driven innovation in engineering education on the basis of recent research results. All the trends analyzed here have the student as the ultimate target stakeholder, so these trends are framed within the area known as learning analytics (Ferguson, 2012). However, the collection and processing of data for decision-making have a twofold side and are not without risks, some of which are also discussed in this paper. This is precisely the structure followed in the rest of this paper, with section 2 discussing trends on data-driven innovation in engineering education, section 3 dedicated to discussing associated risks, and section 4 presenting the conclusions of this work.
2. SOME TRENDS ON DATA-DRIVEN INNOVATION IN ENGINEERING EDUCATION
One of the most important trends in data-driven innovation for engineering education is the improvement of educational content. Educational content may include, for example, video lectures, automatic correction exercises, and other additional resources (texts, animations, simulations, etc.). Nowadays, it is possible to collect low-level data related to the interaction of each learner with each educational resource, including (Ruipérez-Valiente, Muñoz-Merino, Leony, & Delgado Kloos, 2015) when the learner starts to play a video, when the learner stops a video, number of seconds of the video watched by the learner, when the learner attempts an automatic correction exercise, number of attempts in each automatic correction exercise by the learner, learning sequence followed by the learner when moving between educational resources, etc. With this low-level data, it is possible to detect videos or exercises that are not working correctly and that need to be improved. Some high-level indicators that contribute to detecting video lectures that need to be revised are: a high number of repetitions in a fragment of a video (which typically denotes a complex explanation or an error in that fragment), and a high percentage of students who do not watch a video from the beginning to the end (which typically denotes inappropriate content for the student’s level or lack of engagement in the teacher’s explanation). Some high-level indicators that contribute to detecting automatic correction exercises that need to be revised are: a very low number of incorrect answers in formative exercises (which typically denotes very simple exercises that may cause boredom and waste students’ time), and a very high number of incorrect answers in summative exercises (which typically denotes very complex exercises that may cause frustration as students are not well prepared to solve those exercises).
Another important trend in data-driven innovation in engineering education refers to the improvement of social interactions among learners, and applies typically to courses with a very large number of students, either online or blended courses, and where teachers cannot provide personalized assistance due to the very large number of social interactions that take place in the course. Research in this line focused on characterizing the social interactions produced in a course, and on proposing methods and visualizations to help teachers make decisions about how to improve their course design. For example, there have been research studies which detected that the most appropriate tool to manage social interaction in courses with a very large number of students is the built-in forum provided by the learning platforms (Alario-Hoyos, Pérez-Sanagustín, Delgado-Kloos, Parada G., & Muñoz-Organero, 2014). Some other research studies focused on the identification of leaders within the community of learners, characterizing these leaders as the most active students in the course forum (Alario-Hoyos, Muñoz-Merino, Pérez-Sanagustín, Delgado Kloos, & Parada G., 2016). This identification of leaders is
