This article addresses the design of activity generators in the context of serious games for declarative knowledge training. Designing these generators is a complex task requiring specific knowledge and guidance, whic...
ISBN:
(纸本)9783031723148;9783031723155
This article addresses the design of activity generators in the context of serious games for declarative knowledge training. Designing these generators is a complex task requiring specific knowledge and guidance, which falls under the scope of research in engineering. Our proposal is a design and implementation framework for generators of training game activities. The framework is a model and metamodel oriented software infrastructure that must be extended for domain specific facts. The resulting generators provide adapted and varied training activities in the form of dungeon levels for Roguelite-oriented games.
In learning programming, it is important to learn from the best of other people's code. So far, we have developed a code-sharing platform with a mechanism for sharing only the code of others who are close to the l...
ISBN:
(纸本)9783031601248;9783031601255
In learning programming, it is important to learn from the best of other people's code. So far, we have developed a code-sharing platform with a mechanism for sharing only the code of others who are close to the learner's level. We believe that sharing code that is close to learners' strategies is beneficial for helping them learn from others, so in this study we propose a method for evaluating the strategies of code and a method for calculating the closeness of strategies as similarity. We implemented a filtering method that displays only code with a certain level of similarity to the ranking, and conducted experiments to compare the rankings of our proposed method and the conventional method for expert programmers. The results suggest that the ranking of our method promotes better learning.
In everyday life, adaptive behavior depends on the ability to perceive action possibilities. The field of research on affordances has addressed how individuals perceive action possibilities through the coupling betwee...
ISBN:
(纸本)9783031552441;9783031552458
In everyday life, adaptive behavior depends on the ability to perceive action possibilities. The field of research on affordances has addressed how individuals perceive action possibilities through the coupling between the perceiver's capacity and environmental features. However, with the increasing digitalization of our environment, people usually need to perceive action boundaries in a 2D-cyberspace. Consequently, researchers need new tasks to operationalize action boundary perception in 2D-cyberspace. The current article aims to propose a critical review of two action boundary perception tasks: the Perception-Action Coupling Task and the Action Boundary Perception Online Task, as assessment tools of the virtual action-boundary perception in digital environment. First, we present the historical background and context of the emergence of these tasks. Then, we review the studies that have employed these tasks. Finally, we conclude by discussing the potential of these tasks, as well as providing a critical description of the limitations that future research will need to address.
In recent times, Massive Open Online Courses (MOOCs) have become increasingly popular for offering accessible and versatile learning opportunities to a broad audience. However, specific tasks that are necessary in suc...
ISBN:
(纸本)9783031630279;9783031630286
In recent times, Massive Open Online Courses (MOOCs) have become increasingly popular for offering accessible and versatile learning opportunities to a broad audience. However, specific tasks that are necessary in such systems and usually require human involvement, like grading assignments, can be difficult to automate and scale. Furthermore, recent studies have highlighted the capabilities of Large Language Models (LLMs) in a variety of natural language processing tasks, yet the effectiveness of these models in evaluating assignments in educational settings like MOOCs is still an under-researched field. In this paper, we introduce a novel multi-agent architecture, powered by LLMs and the AutoGen framework, that aims in automating the grading of subject-agnostic student assignments. Additionally, we present interaction examples between the agents during grading coding assignments, shedding light on the system's potential to mimic human-like grading nuances and incorporate the tutor's feedback. This research aims to demonstrate the advancements in automated grading, emphasizing the role of multi-agent systems in educational technology.
Legal regulations and conceptual models are important for public organizations. Conceptual models are means for complexity reduction in the design and customization of information systems. Legal regulations are import...
ISBN:
(数字)9783031708046
ISBN:
(纸本)9783031708039;9783031708046
Legal regulations and conceptual models are important for public organizations. Conceptual models are means for complexity reduction in the design and customization of information systems. Legal regulations are important for public organizations as they specify the services that the organizations offer to citizens and businesses. However, the operationalization of legal regulations is challenging because they leave room for interpretation and there is a high number of involved actors. These actors comprise of domain experts and IT experts within a public organization, but also other public organizations on the same or different levels of government. In consequence, there are many actors involved in the operationalization and execution of legal regulations for public services who would benefit from the use of conceptual models. To provide support for these actors, we address the following research goal: Design of a method for the collaborative and semi-automated generation of conceptual model from legal regulations in public organizations. In the course of our design science research approach, we derived requirements for the solution based on interviews with thirteen public officials. We conceptually developed the method and evaluated it with an illustrative scenario and expert interviews with six public officials. The evaluations reveal the general potential usefulness and intended use of our method.
Generative Artificial Intelligence empowered conversational agents (chatbots) seem to be increasingly used in various settings including education. While student teachers are key stakeholders in supporting and improvi...
ISBN:
(纸本)9783031630279;9783031630286
Generative Artificial Intelligence empowered conversational agents (chatbots) seem to be increasingly used in various settings including education. While student teachers are key stakeholders in supporting and improving education, not many studies exist in student teachers' views on the educational use of chatbots. The current study performs a usability evaluation and explores student teachers' views on the academic use of the VIP-Bot, an advanced academic Discord chatbot, which leverages the OpenAI's gpt-3.5-turbo-instruct model. Student teachers, within the context of the formative task of writing a literature review, interacted with the chatbot and self-reported their experiences through an online survey. The usability evaluation returned a relatively high SUS score (76.36) for the chatbot. Moreover, student teachers' view on the chatbot acceptance, effectiveness and motivation were positive. The chatbot can be helpful in developing ideas and initiating further engagement with the literature. Academic misconduct concerns have been expressed if the chatbot is not used properly. The study, as a usability evaluation, is an essential step in further chatbot development and, as an investigation of student teachers' views, it is an essential step on the chatbot employment in teaching and learning.
Tools for discovering learning resources become increasingly important as more and more educational offerings move online. Improvements in the retrieval or recommendation of these resources often rely on the availabil...
ISBN:
(纸本)9783031724398;9783031724404
Tools for discovering learning resources become increasingly important as more and more educational offerings move online. Improvements in the retrieval or recommendation of these resources often rely on the availability of metadata. For example, it has been demonstrated that showing teachers educational metadata alongside the search result could improve search outcomes. However, this relies on relevant educational metadata being embedded in web pages using formats such as JSON-LD or MicroData. For learning resources, the Learning Resource Metadata Initiative (LRMI) ontology defines classes and properties to express such embedded educational metadata. Previous studies have assessed its adoption, quality, and conformance to the ontology prior to an LRMI version update in 2020. This contribution updates prior studies with respect to adoption following the version change. We then focus on mining usage patterns of LRMI properties for the benefit of application developers who would like to leverage this resource. We also expand our analysis beyond just resources that use LRMI by training a text classifier to identify educational web pages. As a result, we are able to present what we believe to be the broadest and most recent examination of usage patterns and adoption of learning resource metadata on the web.
This paper explores the extent to which ChatGPT can be used to combat visual ageism, i.e., "the social practice of visually underrepresenting older people or misrepresenting them in a prejudiced way" [1, p.1...
ISBN:
(纸本)9783031615450;9783031615467
This paper explores the extent to which ChatGPT can be used to combat visual ageism, i.e., "the social practice of visually underrepresenting older people or misrepresenting them in a prejudiced way" [1, p.164] on websites. First, insights from earlier empirical studies on visual ageism are presented to illustrate how ageist pictures can be injurious to older people and how to combat this. Then, a chat session with ChatGPT will be used to discover whether the tool can generate reliable advice on how to counter visual ageism on websites. Finally, ChatGPT's advice will be evaluated from a scientific point of view.
In this paper, we introduceQuizMaster, an innovative web-based adaptive learning system designed for conducting formative assessment on-demand anytime during students' course study. QuizMaster reduces learner time...
ISBN:
(纸本)9783031630279;9783031630286
In this paper, we introduceQuizMaster, an innovative web-based adaptive learning system designed for conducting formative assessment on-demand anytime during students' course study. QuizMaster reduces learner time spent on assessment and accelerates formative feedback delivery. Leveraging a MultiArmed Bandit algorithm for question sequencing and feedback, it ensures intelligent assessment processes. Additionally, we employ Large Language Models to auto-generate questions, enhancing instructor productivity. When deployed, QuizMaster will serve to assess adaptive algorithms for formative assessment in realworld learning scenarios. Through our detailed analysis of the QuizMaster architecture, we demonstrate how to leverage reinforcement learning and generative intelligence in the development of systems for formative assessment.
Extensive computational research has been dedicated to detecting keys and modes in tonal Western music within the major and minor modes. Little research has been dedicated to other modes and musical expressions, such ...
ISBN:
(纸本)9783031606373;9783031606380
Extensive computational research has been dedicated to detecting keys and modes in tonal Western music within the major and minor modes. Little research has been dedicated to other modes and musical expressions, such as folk or non-Western music. This paper tackles this limitation by comparing traditional template-based with unsupervised machine-learning methods for diatonic mode detection within folk music. Template-based methods are grounded in music theory and cognition and use predefined profiles from which we compare a musical piece. Unsupervised machine learning autonomously discovers patterns embedded in the data. As a case study, the authors apply the methods to a dataset of Irish folk music called The Session on four diatonic modes: Ionian, Dorian, Mixolydian, and Aeolian. Our evaluation assesses the performance of template-based and unsupervised methods, reaching an average accuracy of about 80%. We discuss the applicability of the methods, namely the potential of unsupervised learning to process unknown musical sources beyond modes with predefined templates.
暂无评论