Kitabı oku: «Innovando la educación en la tecnología», sayfa 4

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 important to facilitate teachers’ work, as leaders can act as a bridge between the faculty and the rest of the students, even receiving special roles to be able to curate forum messages. Some other research studies focused on analyzing the overall class mood from social interactions, calculating the polarity of messages (positive, neutral, negative) posted by students in the course forum. The polarity of messages was calculated by applying word dictionaries and syntax rules, and the aim was to detect parts of the course in which the overall class mood was more positive or more negative to take corrective measures in the second case (Moreno-Marcos, Alario-Hoyos, Muñoz-Merino, Estévez-Ayres, & Delgado Kloos, 2018). Finally, all the data collected from social interactions can be used as input to develop chatbots or conversational agents programmed to give support to students in specific courses (Delgado Kloos, Catalán-Aguirre, Muñoz-Merino, Alario-Hoyos, 2018).

An additional relevant trend in data-driven innovation in engineering education is the study, characterization, and support of students’ development of self-regulated learning (SRL) skills. SRL skills are particularly important in engineering education due to, among other things, the complexity of the contents and the permanent retraining demanded in today’s engineers. Appropriate strategies to self-regulate each one’s learning should be applied in every learning stage (before, during, and after each learning activity), including, for instance, setting reasonable and measurable objectives (before), seeking help when necessary (during), self-reflecting on the work done and the objectives achieved (after), etc. (Alonso-Mencía, Alario-Hoyos, Maldonado-Mahauad, Estévez-Ayres, Pérez-Sanagustín, & Delgado Kloos, 2019). The study and characterization of SRL skills in engineering courses led to the conclusion that strategies related to appropriate time management are the most problematic ones for learners. Therefore, specific interventions need to be done to facilitate time management, both when designing a course and when developing support tools (Alario-Hoyos, Estévez-Ayres, Pérez-Sanagustín, Delgado Kloos, & Fernández-Panadero, 2017). It is also important to support students’ self-reflection by offering high-level visualizations based on low-level data with the aim to increase students’ awareness on the desired level to be achieved and that of their classmates, both for an entire course and for each module or part of a course (Ruipérez-Valiente, Muñoz-Merino, Leony, & Delgado Kloos, 2015).

One last, but not least, relevant trend in data-driven innovation in engineering education is the prediction of students’ behavior from previously collected data and appropriately trained machine learning models. The variables that are typically predicted through these models refer to students’ partial or final grades in a course; and also to whether a student will abandon a course or not; and, by extension, to whether a student will abandon a complete study program (bachelor’s degree or master’s degree) or not. The aim of these prediction models is to take corrective measures in order to prevent students from failing a course, or from dropping out of a course or study program. Studies on prediction in education have detected that, in general, low-level data, such as the interaction with educational content (e.g., videos and exercises), have greater predictive power than data collected from self-reported questionnaires (such as students’ intentions and motivations) (Moreno-Marcos, Alario-Hoyos, Muñoz-Merino, & Delgado Kloos, 2018). There are still important gaps in this research line, including proposing generalizable models applicable to different educational contexts and areas of knowledge, and developing predictive models and tools for real-time data collection and processing in order to improve the implementation of corrective measures.

3. SOME RISKS OF DATA-DRIVEN INNOVATION IN ENGINEERING EDUCATION

The collection and processing of data for decision-making in engineering education is not without problems. In fact, there are important risks to worry about, which have been highlighted by numerous experts on learning analytics, educational data mining, and data protection policies, (Dringus, 2012) (Khalil, Taraghi, & Ebner, 2016), as well as certain ethical considerations (Slade, & Tait, 2019). Some of these risks are briefly described in this section, although each of them would deserve an entire paper for discussion.

A first problem refers to the secure storage of collected data. Many institutional education systems are not prepared to store large amounts of data in a secure way and are likely to have breaches that can compromise important data, including students’ personal data. Relying on third-party services for data storage in the cloud can also lead to an inappropriate use of the data collected by these service providers.

A second problem refers to data privacy. It is very important to have an institutional strategy that clearly states what data needs to be collected from students and who has access to the data. Many educational institutions are not aware of all the data they collect (or can potentially collect); do not have mechanisms to control who has access to the data collected; and/ or do not have an internal policy to facilitate that the right people can make proper informed decisions, being able to access the data they are entitled to.

A third problem refers to always getting explicit consent from the students for collecting data. It is very important that students (who actually own the data) know at all times what data are being collected from them and for what purpose the data are going to be used. In addition, there are international laws such as the GDPR (General Data Protection Regulation) in Europe that require, among other things, the removal of data collected upon request by its owner. Many educational institutions do not have data collection ethics committees and are not prepared to delete collected data upon request.

A fourth problem refers to transparency, or rather lack of transparency, of many algorithms and systems which are private and whose code is not open. The lack of transparency prevents algorithms and systems from being audited to better understand how they work. Even if one relies on third-party algorithms and systems to make informed decisions, it is important to know how the results and visualizations they provide were obtained.

A fifth problem refers to bias. Many artificial intelligence systems use data collected in the past to make their calculations and predictions. However, data collected in the past may have important biases, such as a gender imbalance, which could lead to promoting more male students versus female students or vice versa. In general, it is important to take minorities into account when using data from the past as input so that these are not penalized.

Finally, it is important to bear in mind that humans may misinterpret the results and visualizations obtained from the data processed. Sometimes there are people who deliberately twist the data to fit a pre-designed theory, instead of discarding this theory if data advise to do so. Actually, from a very large dataset, and taking only a subset of it, erroneous and unreproducible conclusions can be very easily reached.

4. CONCLUSIONS

Innovation in engineering education must be informed by data. Teachers must be aware of their students’ performance (individually and at the class level) to support those who need more help as well as offer top quality educational resources progressively improved according to the data collected. Students should define a curriculum adapted to their particular needs and develop their SRL skills. Institutions must create specialized units for data collection and processing, and adequately train their staff (including teachers) for a data management culture. Nevertheless, there are numerous risks to be aware of, and a trade-off is needed so that these risks do not slow down innovation in educational institutions.

REFERENCES

Alario-Hoyos, C., Pérez-Sanagustín, M., Delgado-Kloos, C., Parada G., H. A., & Muñoz-Organero, M. (2014). Delving into participants’ profiles and use of social tools in MOOCs. IEEE Transactions on Learning Technologies, 7(3), 260-266.

Alario-Hoyos, C., Muñoz-Merino, P. J., Pérez-Sanagustín, M., Delgado Kloos, C., & Parada G., H. A. (2016). Who are the top contributors in a MOOC? Relating participants’ performance and contributions. Journal of Computer Assisted Learning, 32(3), 232-243.

Alario-Hoyos, C., Estévez-Ayres, I., Pérez-Sanagustín, M., Delgado Kloos, C., & Fernández-Panadero, C. (2017). Understanding learners’ motivation and learning strategies in MOOCs. Intern. Review of Research in Open and Distributed Learning, 18(3), 119-137.

Alario-Hoyos, C., Estévez-Ayres, I., Delgado Kloos, C., Villena-Román, J., Muñoz-Merino, P. J., & Llorente-Pérez, E. (2019). Redesigning a freshman engineering course to promote active learning by flipping the classroom through the reuse of MOOCs. International Journal of Engineering Education, 35(1), 385-396.

Alonso-Mencía, M. E., Alario-Hoyos, C., Maldonado-Mahauad, J., Estévez-Ayres, I., Pérez-Sanagustín, M., & Delgado Kloos, C. (2019). Self-regulated learning in MOOCs: lessons learned from a literature review. Educational Review (published online), 1-27.

Baepler, P., Walker, J. D., & Driessen, M. (2014). It’s not about seat time: Blending, flipping, and efficiency in active learning classrooms. Computers & Education, 78, 227-236.

Delgado Kloos, C., Catalán-Aguirre, C., Muñoz-Merino, P. J., Alario-Hoyos, C. (2018). Design of a Conversational Agent as an Educational Tool, In Learning with MOOCs 2018 (LWMOOCS V) (pp. 27-30). IEEE.

Dringus, L. P. (2012). Learning analytics considered harmful. Journal of Asynchronous Learning Networks, 16(3), 87-100.

Ferguson, R. (2012). Learning analytics: drivers, developments and challenges. International Journal of Technology Enhanced Learning, 4(5/6), 304-317.

Khalil, M., Taraghi, B., & Ebner, M. (2016). Engaging Learning Analytics in MOOCs: the good, the bad, and the ugly. In Proceedings of the International Conference on Education and New Developments (END) (pp. 3-7).

Moreno-Marcos, P. M., Alario-Hoyos, C., Muñoz-Merino, P. J., & Delgado Kloos, C. (2018). Prediction in MOOCs: A review and future research directions. IEEE Transactions on Learning Technologies (published online), 1-19.

Moreno-Marcos, P. M., Alario-Hoyos, C., Muñoz-Merino, P. J., Estévez-Ayres, I., & Delgado Kloos, C. (2018). Sentiment Analysis in MOOCs: A case study. In 2018 IEEE Global Engineering Education Conference (EDUCON) (pp. 1489-1496). IEEE.

Pérez-Sanagustín, M., Hilliger, I., Alario-Hoyos, C., Delgado Kloos, C., & Rayyan, S. (2017). H-MOOC framework: reusing MOOCs for hybrid education. Journal of Computing in Higher Education, 29(1), 47-64.

Ruipérez-Valiente, J. A., Muñoz-Merino, P. J., Leony, D., & Delgado Kloos, C. (2015). ALASKA: A learning analytics extension for better understanding the learning process in the Khan Academy platform. Computers in Human Behavior, 47, 139-148.

Slade, S., & Tait, A. (2019). Global guidelines: Ethics in learning analytics. Oslo: International Council for Open and Distance Education (ICDE).

Zimmerman, B. J. (2013). Theories of self-regulated learning and academic achievement: An overview and analysis. In Self-regulated learning and academic achievement (pp. 10-45). Routledge.

Building Blocks for Powerful Ideas: Designing a Programming Language to Teach the Beauty and Joy of Computing

Jens Mönig

jens.moenig@sap.com / Research Expert SAP, Germany

Recepción: 9-8-2019 / Aceptación: 21-8-2019

ABSTRACT. Snap! is a cloud-native graphical programming environment and an online community. It is the programming language made for UC Berkeley’s popular introductory CS course named “The Beauty and Joy of Computing”. Snap! is taught in colleges and high schools across the U.S. from Palo Alto to Philadelphia. It has been translated to more than 40 languages and is used around the world—from Göttingen to Beijing—for teaching and research. Snap! has been designed for inclusion. Its low floor welcomes beginners and its multi-media capabilities invite creative thinkers of all ages. At the same time, Snap! offers sophisticated abstractions that make it suitable for an intellectually rigorous introduction to computer science.

KEYWORDS: Snap!, BJC, AP CSP, CS0.

Construyendo bases sólidas para ideas poderosas: diseñando un lenguaje de programación para enseñar la belleza y alegría de la informática

RESUMEN. Snap! es un entorno de programación gráfica nativo de la nube y una comunidad en línea. Es el lenguaje de programación creado para el popular curso introductorio de CS de UC Berkeley llamado “La belleza y la alegría de la informática”. Snap! se imparte en colegios y escuelas secundarias de los EE. UU., desde Palo Alto hasta Filadelfia. Se ha traducido a más de 40 idiomas y se utiliza en todo el mundo, desde Gotinga hasta Beijing, para la enseñanza y la investigación. Snap! ha sido diseñado para su inclusión. El nivel bajo le da la bienvenida a principiantes y sus capacidades multimedia que invitan a pensadores creativos de todas las edades. Al mismo tiempo Snap! ofrece abstracciones sofisticadas que lo hacen adecuado para una introducción intelectualmente rigurosa a la informática.

PALABRAS CLAVE: Snap!, BJC, AP CSP, CS0.

1. INTRODUCTION

Recent years have seen a thunderous revival of programming education, sparked by a growing demand for computationally skilled workforce and spearheaded by MIT’s visual Scratch language. In Scratch’s wake, a new class of so-called “blocks-based” programming editors has appeared, and visual coding has since evolved into the de-facto standard for introductory CS activities. Along with Scratch’s metaphor of stacking bricks, representing chunks of code into program-“towers” that are executed from top to bottom, a very traditional imperative style of programming has been established as quasi-best practice for introducing children and novices to CS.

At the same time, driven by the asynchronous nature of web programming and massive parallelization on the backend side to cope with “big data”, many professional text-based programming languages have been revamped to support functional programming techniques such as proper tail-calls and even lambda, which before were considered too exotic to become mainstream. The gap between what beginners are exposed to in visual blocks-based languages and what is required to express themselves in a professional modern programming language today is more than just syntax. The gap is also conceptual and calls for proficiency in paradigms.

2. A CHALLENGE

Frequently discussed among educators is how to foster the transition from visual to textual programming. Sometimes the proposed solutions suggest bi-modal code editing, being able to switch back and forth between blocks and text. While this might address the lesser issue of coping with textual syntax, it does not help with introducing concepts and paradigms unsupported by any one side, and in the worst case even impoverishes the beginner’s programming experience to the least common denominator of two programming languages.

On the other side of the spectrum, efforts are under way to broaden the scope and raise the ceiling of blocks-based programming. I will present one such project: Snap! Build Your Own Blocks. Snap! is a Scratch-like programming language that treats code blocks as first-class citizens instead of confining them to an editing modality. Embracing nested data structures and higher order functions, Snap! lets learners create arbitrary control structures and even custom programming languages with just blocks. Snap! has been developed for UC Berkeley’s introductory computer science course named “The Beauty and Joy of Computing”.

3. IN THIS TALK

I will share thoughts on the design of Snap! in a live-programmed excursion touching on a selection of powerful ideas from algorithms to artificial intelligence.

PONENCIAS

Análisis de sentimientos de noticias escritas usando un modelo basado en la red neuronal long short-term memory para determinar si las noticias positivas mejoran el estado de ánimo de las personas

Gustavo Adolfo Reyes-Paredes

kivada@icloud.com / Universidad de Lima, Perú

Recepción: 17-6-2019 / Aceptación: 8-8-2019

RESUMEN. Es un hecho que el paradigma de distribuir noticias negativas a la población es el más aceptado mundialmente. Una gran cantidad de investigaciones se han enfocado en establecer los efectos de este paradigma en la población y, en todos los casos, se ha demostrado que es dañino para la salud y el comportamiento de las personas. Por ello, se ha decidido demostrar que el paradigma opuesto, la distribución de noticias positivas, genera una mejora en la salud, en el comportamiento y en el estado de ánimo de la población. Para lograr este propósito, se desarrolló un modelo basado en la red neuronal long short-term memory para realizar el análisis de los sentimientos relacionados con las noticias escritas en español. El experimento consistió en determinar el estado de ánimo de las personas luego de haber leído noticias positivas.

PALABRAS CLAVE: aprendizaje de máquinas, análisis de sentimientos, red neuronal recurrente, long short-term memory, bienestar psicológico y social

Sentiment Analysis of Written News Using a Model Based on the Long Short-Term Memory Neural Network to Determine if Positive News Improve People’s Mood

ABSTRACT. It is a fact that the paradigm of distributing negative news to the population is the most accepted worldwide. A large amount of research has been done to determine the effects of this paradigm on the population and, in all cases, it has been shown to be harmful to the health and behavior of people. Therefore, this paper aims to demonstrate that the opposite paradigm, the distribution of positive news, generates an improvement in the health, behavior and mood of the population. To achieve this, a model based on the long short-term memory neural network has been developed in order to analyze sentiments caused by news written in Spanish. Moreover, an experiment was conducted to determine people’s mood after having read positive news.

KEYWORDS: machine learning, sentiment analysis, recurrent neural network, long short-term memory, psychological and social well-being