Search

Owing to the predominant role of Machine Learning(ML) across domains, it is being introduced at multiple levels of education, including K-12. Researchers have leveraged games, augmented reality and other ways to make learning ML concepts interesting. However, most of the existing games to teach ML concepts either focus on use-cases and applications of ML instead of core concepts or directly introduce ML terminologies, which might be overwhelming to school students. Hence, in this paper, we propose ML-Quest, a game to incrementally present a conceptual overview of three ML concepts: Supervised Learning, Gradient Descent and K-Nearest Neighbor (KNN) Classification. The game has been evaluated through a controlled experiment, for its usefulness and player experience using the TAM model, with 41 higher-secondary school students. Results show that students in the experimental group perform better in the test than students in the control group, with 5% of students in the experimental group scoring full marks. However, none of the students in the control group could score full marks. The survey results indicate that around 77% of the participants who played the game either agree or strongly agree that ML-Quest has made their learning interactive and is helpful in introducing them to ML concepts. [ABSTRACT FROM AUTHOR]

PS-I learning approaches with an initial problem-solving phase (PS) followed by an instruction phase (I) can be optimised by providing adaptive (individualised) instruction that builds on students' problem-solving products. A computer-based implementation of both phases offers the possibility of adaptivity at the transition from the problem-solving to the instruction phase. However, it also poses two challenges for the problem-solving phase, which should allow for (1) complex problem-solving processes (process validity) and (2) accurate diagnosis of problem-solving products. Increased openness of the learning environment can increase the process validity and decrease diagnostic accuracy and vice-versa (complexity-accuracy trade-off). Using two variants of a computer-based learning environment for fraction comparison with different extent of openness (O+ and O-), we investigate whether both requirements (complex problem-solving processes and accurate diagnosis of the problem-solving products) can be met simultaneously. To check process validity (complexity of problem-solving processes), we compare the problem-solving products with those from previous research on an analogous paper-based version. Our results show that valid and comparable problem-solving processes can be achieved in both computer-based learning environments (O+ and O-). Moreover, only the learning environment O- enables an accurate computer-based interpretation of students' products and thus resolving the complexity-accuracy trade-off. [ABSTRACT FROM AUTHOR]

This study was to review empirical studies on UAV usage in education. 43 papers were selected and reviewed with respect to the following dimensions: (1) publication time and source, (2) methodology in reviewed studies, and (3) main findings reported by researchers. The results showed that the highest number of published articles was between 2018 and 2020, and that most studies were published in journals and conference proceedings. Most participants were undergraduate students from Asia. Most studies were conducted for five days or less and the most frequent domain to which UAV was applied was STEM. Scholars often used questionnaires and tests as measurement instruments. We found that the most frequent learning activities were collecting data with UAV, learning how to fly UAV, introducing UAV, working in the field with UAV, and programming UAV. Research variables that scholars explored in reviewed studies often were learning performance, attitude and motivation. The main findings concerned skills, knowledge, motivation and responsibility. The advantages of UAV in education were accessing data from inaccessible or dangerous locations, collecting and delivering temporal and spatial resolution information quickly etc., disadvantages were availability issues, legal issues, logistical issues, and privacy and ethics issues. [ABSTRACT FROM AUTHOR]

English for Specific Purposes (ESP) teacher development has become a crucial issue in ESP teaching and research. How to equip ESP teachers with necessary knowledge and skills in the digital era becomes a hot topic. A Personal Learning Environment (PLE) is a potential pedagogical approach to realize learning-centered in ESP teacher development. This paper is an exploratory research which attempts to integrate Learning Management System (LMS) with Personal Learning Environment for the training of ESP teachers at tertiary education in China. Based on the previous research on the seven-factor technology, pedagogy, and content knowledge (TPACK) framework and the five-factor skill Framework for ESP teachers in China, a PLE-ESP platform was built in the form of a website (). The platform was evaluated with 20 ESP participants within a two-month pilot study. A survey about the value and flexibility of the platform was carried out, the result of which indicated an improvement on the skills required in ESP teaching, learners' self-regulated learning competency and their ICT literacy. Recommendations were made for future research on the successful integration and maintenance of PLE and LMS. [ABSTRACT FROM AUTHOR]

Textual data, as a key carrier of learning feedback, is continuously produced by many students within course forums. The temporal nature of discussion requires students' emotions and concerned aspects (e.g. teaching styles, learning activities, etc.) to be dynamically tracked for understanding learning requirements. To characterize dynamics of emotion-aspects, this paper presents an unsupervised model, namely temporal emotion-aspect model (TEAM), modeling time jointly with emotions and aspects to capture emotion-aspect evolutions over time. Especially, the primary output of TEAM is two-fold: emotion-specific aspect probabilistic distributions and their evolutions over time. With the discussion data from two online course forums, we validated the performance of TEAM and utilized this model to discover most concerned emotion-aspects as well as their evolutionary trends for the whole learning group and different achievement levels of groups, respectively. The results indicated that, (1) content-related aspects were the main focus with higher probabilities to negative and confused emotions; (2) there were higher probabilities of emotional expressions in the initial and final stages of a semester; (3) compared with high- and medium-achieving students, low-achieving students were less active in emotional engagement on the whole, and tended to express more confusion in the final stage of a semester. [ABSTRACT FROM AUTHOR]

Process mining methodologies are designed to uncover underlying business processes, deviations from them, and in general, usage patterns. One of the key limitations of these methodologies is that they struggle in cases in which there is no structured process, or when a process can be performed in many ways. Learning Management Systems are a classic case of unstructured processes since each learner follows a different learning process. In this paper, we address this limitation by proposing and validating the user behavior pattern detection (UBPD) methodology which is based on detecting very short user activities and clustering them based on shared variance to construct a more meaningful behavior. We develop and validate this methodology by using two datasets of unstructured processes from different implementations of a learning management system. The first dataset uses a gamified course where users have the freedom to choose how to use the system, and the second dataset uses data from a massive online open course, where again, system usage is based on personal learning preferences. The key contribution of the methodology is its ability to discover user-specific usage patterns and cluster users based on them, even in noisy systems with no clear process. It provides great value to course designers and teachers trying to understand how learner interact with their system and sets the foundation for additional research in this class of systems. [ABSTRACT FROM AUTHOR]

This paper presents the findings of a mixed-methods research that explored the potentials emerging from aligning learning design (LD) and learning analytics (LA) during the design of a predictive analytics solution and from involving the instructors in the design process. The context was a past massive open online course, where the learner data and the instructors were accessible for posterior analysis and additional data collection. Through a close collaboration with the instructors, the details of the prediction task were identified, such as the target variable to predict and the practical constraints to consider. Two predictive models were built: LD-specific model (with features based on the LD and pedagogical intentions), and a generic model (with cumulative features, not informed by the LD). Although the LD-specific predictive model did not outperform the generic one, some LD-driven features were powerful. The quantity and the power of such features were associated with the degree to which the students acted as guided by the LD and pedagogical intentions. The leading instructor's opinion about the importance of the learning activities in the LD was compared with the results of the feature importance analysis. This comparison helped identify the problems in the LD. The implications for improving the LD are discussed. [ABSTRACT FROM AUTHOR]

Learning analytics research has used both knowledge engineering and machine learning methods to model student behaviors within the context of digital learning environments. In this paper, we compare these two approaches, as well as a hybrid approach combining the two types of methods. We illustrate the strengths of each approach in the context of a case study in building models able to detect when students "game the system", a behavior in which learners abuse the environment's support functionalities in order to succeed by guessing or copying answers. We compare the predictive performance, interpretability and generalizability of models created using each approach, doing so across multiple intelligent tutoring systems. In our case study, we show that the machine-learned model required less resources to develop, but was less interpretable and general. In contrast, the knowledge engineering approach resulted in the most interpretable and general model. Combining both approaches in a hybrid model allowed us to create a model that performed best across the three dimensions, but requiring increased resources to develop. [ABSTRACT FROM AUTHOR]

This paper presents a design for a cutting-edge English program in which elementary school learners of English as a foreign language in Taiwan had lively interactions with a teaching assistant robot. Three dimensions involved in the design included (1) a pleasant and interactive classroom environment as the learning context, (2) a teaching assistant robot designed and built by the researchers as instructional technology (instructional tool/medium), and (3) the need for improved motivation and learning outcomes and positive learning experiences of the students as the core research problem. This Human–Robot Interaction (HRI) led to better pedagogical effects on learning and teaching by (1) employing a vivid, enjoyable teaching approach; (2) adopting practical, interesting learning materials; and (3) creating a natural, enjoyable learning context. Both quantitative and qualitative findings of this study indicate that the students' English learning experiences were enhanced, as were their motivation and learning outcomes as a result of this HRI. This paper, instead of merely suggesting design criteria for robots, provides a set of instructional design guidelines that other researchers can follow to create an innovative and enjoyable English classroom that employs an interactive robot as an assistant for enhancing English acquisition while simultaneously reducing the pressure and teaching load of the English instructors. [ABSTRACT FROM PUBLISHER]

Researchers have recognized the potential of educational computer games in improving students’ learning engagement and outcomes; however, facilitating effective learning behaviors during the gaming process remains an important and challenging issue. In this paper, a collaborative knowledge construction strategy was incorporated into an educational computer game to facilitate students’ knowledge sharing and organizing during the game-based learning process. An experiment was conducted to examine the students’ learning behavioral patterns, group efficacy, and problem-solving awareness. The experimental results revealed that the proposed approach improved the students’ learning achievements and awareness of problem-solving. Moreover, from the analysis of the students’ behavior sequences, it was found that, with the collaborative knowledge construction mechanism, the students revealed significantly more aggressive learning behavioral patterns, such as “comparing and observing the learning targets” and “seeking clues and answers” during the gaming process. This implies that integrating the collaborative knowledge construction mechanism into the gaming process has great potential for helping students effectively learn and organize knowledge as well as fostering their awareness of applying the acquired knowledge to dealing with problems. [ABSTRACT FROM PUBLISHER]

Business educators are concerned with integrating diversity-related topics and seek methods by which to teach them. This paper suggests that as classes become more heterogeneous, the opportunity to examine diverse perspectives and experiences naturally arises in the course of class assignments and activities. The differential experiences of majorities and minorities are revealed when students discuss and write about their own experiences related to the content of various business courses. The issues of self and group identity and perceptions of others emerge in the context of small group discussions when students share their experiences as recorded in learning logs, personal cases, research assignments, and typical class discussions. The opportunity for community learning in heterogeneous groups provides a forum for diverse perspectives and experiences to be shared. Students and professors learn about different perceptions and reactions to personal and current events as well as their own perspectives, creating a culture of inclusion in the class. Implications and suggestions for a wider application of our methods to a global context are also offered. [ABSTRACT FROM AUTHOR]

An editorial is presented on focussing on end-users of information systems. Topics include model being widely embraced in education as the foundation theory for many papers on the adoption of learning technology; and incorporating the variables hedonic motivation, price value, and habit while using the model in relation to consumer acceptance of new technology.

This paper reflects on the current position of virtual learning environments (VLEs) in universities and speculates about likely future directions for e-learning. Using accepted models of technology innovation and looking at current Web trends, it considers the extent to which e-learning is truly embedded in institutions, how Web 2.0 is being used by the upcoming generation and what this might mean for teachers, learners and higher education institutions. The paper concludes that optimism about the impact of e-learning on higher education based on the market penetration of VLEs is misplaced and suggests that Ivan Illich's concept of learning webs may be a more reliable guide to future developments. [ABSTRACT FROM AUTHOR]

This paper presents the eight Learning Events Model (8LEM), a pedagogical reference framework which was used, in more than 100 online courses, as a starting point for instructional planning. Besides supporting teachers in early stages of the learning design continuum, the paper shows how this learning/teaching model, as a professional development tool, prompts them to diversify the learning methods experienced by students in their courses. A three-pronged rationale about the importance of this diversification with respect to "mathetic" competence development, epistemology and personalization is also submitted to discussion. [ABSTRACT FROM AUTHOR]

The combination of features in virtual worlds provides an opportunity to implement and research unique learning experiences. With increasing interest and activity from the educational research community, exploring virtual worlds for teaching and learning, there is a need to identify and understand the ethical implications of conducting research in these new environments. This paper examines the traditional ethical concerns within the context of educational research in virtual worlds and identifies how the features of the technology give rise to new ethical dilemmas in the areas of informed consent, privacy protection and identity. [ABSTRACT FROM AUTHOR]

In this paper behavior during the teaching-learning process is modeled by means of a fuzzy cognitive map. The elements used to model such behavior are part of a generic didactic model, which emphasizes the use of cognitive and operative strategies as part of the student-tutor interaction. Examples of possible initial scenarios for the teaching-learning process are developed, along with the results provided by the model. [ABSTRACT FROM AUTHOR]

We present the Personal Learning Environment (PLE) as a practical intervention concerning the organization of technology in education. We explain this by proposing a cybernetic model of the "Personal Learner" using Beer's Viable System Model (VSM). Using the VSM, we identify different regulatory mechanisms that maintain viability for learners, and how physical engagement with tools is of fundamental importance in learners being able to manage their learning environment. We explain how the PLE, in exploiting Service Oriented Architecture, attempts to address this issue of the engagement with tools by allowing learners to control their own instrumentation. This, however, is more than a practical issue. In shifting the locus of control over learning to the learner, the ways in which learners exercise that control becomes an important educational issue. Drawing on sources ranging from Bandura's work on self-efficacy, and philosophical work on social ontology, we argue that self-regulation and technological personalization are issues which strike at the heart of current debates about the organization of education and the nature of the relationship between institutions and learners, and more deeply, the human condition in the modern world. Some anecdotal practical implications are reported in the final section of the paper as we describe the response of learners to the challenges of increased personalization. [ABSTRACT FROM AUTHOR]

Positioning in learning networks is a process that assists learners in finding a starting point and an efficient route through the network that will foster competence building. In the past we have explored computational approaches to positioning based on the contents of the learning network and the behaviour of those participating in it, more or less ignoring different efforts to stimulate positioning and competence development from a top-down perspective. In this paper we introduce a research agenda for positioning in learning networks, discuss several cases and give an outlook on the development of a positioning service for learning networks. [ABSTRACT FROM AUTHOR]

Scaffolding has proven an especially interesting and promising area for supporting teaching and learning practices. Particular interest has emerged in scaffolding student learning in technology-enhanced environments. In this paper, we discuss how scaffolding is implemented in technology-enhanced environments, provide an overview of scaffolding processes and techniques in various contexts, and then provide empirically based guidelines for designing scaffolding in technological environments. We examine current research to identify two primary design components, cognitive and interface, and suggest how scaffold design might be improved for more effective use by learners. We conclude by identifying practice and research implications. [ABSTRACT FROM AUTHOR]

Asking learners standardized questions during performance of a self-directed inductive learning task might be a useful way to complement think aloud protocol data. However, asking questions might also scaffold the learning process and thus influence the exact processes one wants to study. In the study described in this paper two groups of learners performed a computerized self-directed inductive learning task in which they conducted experiments to discover the relations between five independent variables and one dependent variable. In one condition, the learners thought aloud, in the other the learners were asked additional standardized questions pertaining to specific reasoning steps during learning. Measures of learning outcome and learning processes were collected. It appeared that the questions did not influence learning outcome. With respect to learning processes no differences were found, except that learners in the no questioning condition more often repeated experiments. It was concluded that the questions do not seem to threaten the validity of research findings. [ABSTRACT FROM AUTHOR]

Within the context of learning technology environments, there is much efforton one hand, at defining metadata for educational content, and on the other,at specifying learner user profiles. However, less attention has been paidto the understanding of the relationship between these two areas of research,in terms of semantic and structural correlations. Based on an implementationof learning object metadata and learner profiles in a learning technologysystem undertaken in the Getting Education Systems Talking Across LeadingEdge Technologies (GESTALT) project, this paper argues that the definitionof a metadata schema and a User Profile should be a joint effort due to thecomplementary nature of these two descriptions in regard to the critical functionsof the educational process. [ABSTRACT FROM AUTHOR]

Variously described as learning, educational, or knowledge objects, reusable curriculum components are said to hold out the promise of easy and low-cost multimedia course creation. These objects can include interactive simulations, multimedia materials, and also Web documents or sites. What is most important in each case is that they can be used and reused by educators across a variety of teaching and learning settings. Using the term “educational objects” to refer generically to these reusable resources, this paper explores the idea of the “object” that underlies the substantial promise associated with them. It undertakes a critical examination of the various definitions and descriptions of educational objects provided in the literature of educational technology and computer science. It concludes by suggesting a new understanding of educational objects that emphasizes community and educational practice rather than technology and software design. [ABSTRACT FROM AUTHOR]

This paper examines the role of tactile perception in conceptual construction of forces and fields. The learning environment includes a simulation of a force field. The force applied by the field on an object is transferred to the learner's hand through a tactile interface designed as a trackball. The learner experiences varying resistance from the trackball when moving an object on the screen. The forces are actually “felt”, exerted on the screen-object as if the learner's hand is immersed in the “field.” We hypothesize that a tactile interface acts as an agent aimed at recruiting the body non-propositional knowledge, for construction of formal physics knowledge on fields of forces. Twelve subjects were asked to explore the structure of several invisible fields through tactile interface, then to design a series of situations that generate current and that energetically trap a particle in a particular area. The results of the study show that s tudents with no background in physics constructed a graphical representation of a field force of a single and double center of forces similar to the formal physics representation, though they had no conceptual background (i.e., vectors, field lines). Based on the tactile information, they constructed a representation of force as a vector, of force lines, equal-force lines (potential lines for particular cases), potential well (“trap”) and motion of a charged particle in a field of forces. We show that computer tactile interface acts as a trigger for access to non-propositional knowledge employed in everyday bodily activity, but not in formal learning. The computer environment turns into a virtual environment, carrying the features of perception within “reality”, providing opportunities for conceptual construction. [ABSTRACT FROM AUTHOR]