Retrieval-Augmented Generation (RAG) systems are increasingly deployed in web-based educational environments, yet transparency can be seen as a primarily ethical, and, too often, optional, concern, rather than foundational. This paper presents design patterns for building transparent RAG systems, derived from developing and deploying SAGE-RAI, an advanced multi-purpose RAG system, in an educational context. Through systematic evaluation combining quantitative rating data (n=26, mean rating=4.62/5) and qualitative interviews (n=4), we demonstrate that transparency serves dual pedagogical and ethical functions. Our empirical findings reveal high user satisfaction (92.3% rating 4-5 stars) while identifying critical tensions between AI assistance and learning independence. Our findings suggest that as RAG systems increasingly mediate access to web-based knowledge, transparency must evolve from an optional feature to an architectural requirement.

This paper explores the use of Generative AI and ChatGPT for improving the production of distance learning materials. We have conducted participatory design workshops involving cross-disciplinary teams of academics and different stakeholders, such as industry partners and learning material designers that are involved in course production at the UK Open University. The main outcome of these workshops is a set of use cases on how Generative AI tools, such as ChatGPT, can be integrated and augment the existing course production and delivery processes to make them more agile and efficient. Following the workshops, we have developed a proof-of-concept tool that can instantly generate introductions and summaries of course material, automatically generate quizzes and tests, as well as automatically identify, categorise, and transform learning activities. A preliminary evaluation performed with members of the course production teams indicated that in 40% of cases AI generated text of 250-500 words is suitable for use in distance learning materials. Overall, the evaluation participants welcome this use of Generative AI, but there are concerns mainly centred on potential for bias, misinformation, and copyright infringement in the generated learning materials.

Blockchain technology has the potential to revolutionise education in a number of ways. In this paper, we explore the applications of Smart Blockchain Badges on data science education. In particular, we investigate how Smart Blockchain Badges can support learners that want to advance their careers in data science, by offering them personalised recommendations based on their learning achievements. This work aims at enhancing data science accreditation by introducing a robust system based on the Blockchain technology. Learners will benefit from a sophisticated, open and transparent accreditation system, as well as from receiving job recommendations that match their skills and can potentially progress their careers. As a result, this work contributes towards closing the data science skills gap by linking data science education to the industry.

This paper presents a case study on teaching network engineering in conjunction with interactive learning resources. This case study has been developed in collaboration with the Cisco Networking Academy in the context of the FORGE project, which promotes online learning and experimentation by offering access to virtual and remote labs. The main goal of this work is allowing learners and educators to perform network simulations within a web browser or an interactive eBook by using any type of mobile, tablet or desktop device. Learning Analytics are employed in order to monitor learning behaviour for further analysis of the learning experience offered to students.

The ‘blockchain’ is the core mechanism for the Bitcoin digital payment system. It embraces a set of inter-related technologies: the blockchain itself as a distributed record of digital events, the distributed consensus method to agree whether a new block is legitimate, automated smart contracts, and the data structure associated with each block. We propose a permanent distributed record of intellectual effort and associated reputational reward, based on the blockchain that instantiates and democratises educational reputation beyond the academic community. We are undertaking initial trials of a private blockchain or storing educational records, drawing also on our previous research into reputation management for educational systems.

Remote labs and online experimentation offer a rich opportunity to learners by allowing them to control real equipment at distance in order to conduct scientific investigations. Remote labs and online experimentation build on top of numerous emerging technologies for supporting remote experiments and promoting the immersion of the learner in online environments recreating the real experience. This paper presents a methodology for the design, delivery and evaluation of learning resources for remote experimentation. This methodology has been developed in the context of the European project FORGE, which promotes online learning using Future Internet Research and Experimentation (FIRE) facilities. FORGE is a step towards turning FIRE into a pan-European educational platform for Future Internet. This will benefit learners and educators by giving them both access to world-class facilities in order to carry out experiments on e.g. new internet protocols. In turn, this supports constructivist and self-regulated learning approaches, through the use of interactive learning resources, such as eBooks.

This paper presents the Forging Online Education through FIRE (FORGE) initiative, which aims to transform the Future Internet Research and Experimentation (FIRE) testbed facilities, already vital for European research, into a learning resource for higher education. From an educational perspective this project aims at promoting the notion of Self-Regulated Learning (SRL) through the use of a federation of highperformance testbeds and at building unique learning paths based on the integration of a rich linked-data ontology. Through FORGE, traditional online courses will be complemented with interactive laboratory courses. It will also allow educators to efficiently create, use and re-use FIRE-based learning experiences through our tools and techniques. And, most importantly, FORGE will enable equity of access to the latest ICT systems and tools independent of location and at low cost, strengthening the culture of online experimentation tools and remote facilities.

Nowadays personalised service provisioning becomes more feasible due to the increasing availability of smart devices, such as smart phones, tablet computers, Personal Digital Assistants and Play stations. These smart devices can dynamically detect the context data and upload them to support other interesting software applications, such as Facebook and Google maps. Context can become richer and more retrievable if links are established for semantically related context data sets. Taking advantage of the recent digital and Web technologies, this paper proposes a novel Linked Context model that applies the Linked Data principles to model and obtain context data from both users and services in one unified framework to support personalised service provisioning at runtime.

Nowadays, more and more distributed digital TV and TV-related resources are published on the Web, such as Electronic Personal TV Guide (EPG) data. To enable applications to access these resources easily, the TV resource data is commonly provided by Web service technologies. The huge variety of data related to the TV domain and the wide range of services that provide it, raises the need to have a broker to discover, select and orchestrate services to satisfy the runtime requirements of applications that invoke these services. The variety of data and heterogeneous nature of the service capabilities makes it a challenging domain for automated web-service discovery and composition. To overcome these issues, we propose a two-stage service annotation approach, which is resolved by integrating Linked Services and IRS-III semantic web services framework, to complete the lifecycle of service annotating, publishing, deploying, discovering, orchestration and dynamic invocation. This approach satisfies both developer's and application's requirements to use Semantic Web Services (SWS) technologies manually and automatically.

We describe a model-driven translation approach between semantic Web service based business process models in the context of the SUPER project. In SUPER we provide a set of business process ontologies for enabling access to the business process space inside the organisation at the semantic level. One major task in this context is to handle the translations between the provided ontologies in order to navigate from different views at the business level to the IT view at the execution level. In this paper we present the results of our translation approach, which transforms instances of BPMO to instances of sBPEL.

Semantic Web services (SWS) aim at the automated discovery and orchestration of Web services on the basis of comprehensive, machine-interpretable semantic descriptions. However, heterogeneities between distinct SWS representations pose strong limitations w.r.t. interoperability and reusability. Hence, semantic level mediation, i.e. mediation between concurrent semantic representations, is a key requirement to allow SWS matchmaking algorithms to compare capabilities of distinct SWS. In that, semantic level mediation requires to identify similarities across distinct SWS representations. Since current approaches to mediate between distinct service annotations rely either on manual one-to-one mappings or on semi-automatic mappings based on the exploitation of linguistic or structural similarities, these are perceived to be costly and error-prone. We propose a mediation approach enabling the implicit representation of similarities across distinct SWS by grounding these in so-called mediation spaces (MS). Given a set of SWS and their respective MS grounding, a general-purpose mediator automatically computes similarities to identify the most appropriate SWS for a given request. A prototypical application illustrates our approach.

Context-adaptive information systems (IS) are highly desired across several application domains and usually rely on matching a particular real-world situation to a finite set of predefined situation parameters. To represent context parameters, semantic and non-semantic representation standards are widely used. However, describing the complex and diverse notion of specific situations is costly and may never reach semantic completeness. Whereas not any situation parameter completely equals another, the number of (predefined) representations of situation parameters is finite. Moreover, following symbolic representation approaches leads to ambiguity issues and does not entail semantic meaningfulness. Consequently, the challenge is to enable fuzzy matchmaking methodologies to match real-world situation characteristics to a finite set of predefined situation descriptions. In this paper, we propose conceptual situation spaces (CSS) which enable the description of situation characteristics as members in geometrical vector spaces following the idea of conceptual spaces. Consequently, fuzzy matchmaking is supported by calculating the semantic similarity between the current situation and prototypical situation descriptions in terms of their Euclidean distance within a CSS. Aligning CSS to existing symbolic representation standards, enables the automatic matchmaking between real-world situation characteristics and symbolic parameter representations. To prove the feasibility, we apply our approach to the domain of e-learning.

Current technologies aimed at supporting processes - whether it is a business or learning process - primarily follow a metadata- and data-centric paradigm. Whereas process metadata is usually based on a specific standard specification - such as the business process modeling notation (BPMN) or the IMS learning design standard - the allocation of resources is done manually at design- time, and the used data is often specific to one process context only. These facts limit the reusability of process models across different standards and contexts. To overcome these issues, we introduce an innovative semantic Web service-based framework aimed at changing the current paradigm to a context-adaptive service-oriented approach. Following the idea of layered semantic abstractions, our approach supports the development of abstract semantic process model-reusable across different contexts and standards - that enables a dynamic adaptation to specific actor needs and objectives. To illustrate the application of our framework and establish its feasibility, we describe a prototypical application in the e-learning domain.

We describe several advanced functionalities of Magpie -- a tool that assists users with interpreting the web resources. Magpie is an extension to the Internet Explorer that automatically creates a semantic layer for web pages using a user-selected ontology. Semantic layers are annotations of a web page, with a set of applicable semantic services attached to the annotated items. We argue that the ability to generate different semantic layers for a web resource is vital to support the interpretation of web pages. Moreover, the assignment of semantic web services to the entities allows users to browse their neighbourhood semantically. At the same time, the Magpie suite offers trigger functionality based on the patterns of an automatically updated semantic log. The benefits of such an approach are illustrated by a semantically enriched browsing history management.

OntoWeaver is our conceptual modelling methodology and a tool that support the specification and implementation of customized web applications. It relies on a number of different types of ontologies to declaratively describe all aspects of a web application. This paper focuses on the OntoWeaver customization framework, which exploits a user model, a customization rule model, and a declarative site model, to enable the design and development of customized web applications at a conceptual level. OntoWeaver makes use of the Jess inference engine to reason upon the site specifications and their underlying site ontologies according to the customization rules and the valuable user profiles to provide customization support in an intelligent way. The ontology-based approach enables the target web applications to be represented in an exchangeable format. Hence, the management and maintenance of web applications can be carried out at a conceptual level without having to worry about the implementation details. Likewise, the declarative nature of the site specifications and the generic customization framework allow the specification of customization requirements to be carried out at the conceptual level.

This research aims at improving dynamic query based information access by using knowledge modelling to narrow the search space. Our objective is to allow users to quickly browse web pages and get the information content related to his/her profile and within semantically relevant dimensions. We have developed an application to link a dynamic query interface to ontologies containing knowledge about customers, products and shopping tasks in an online shop.

This paper presents the framework of an Intelligent Information Presentation System (IIPS), which provides intelligent interface presentation support for data-intensive web-based applications through the use of ontologies to drive the web site generation and maintenance process. IIPS defines a comprehensive set of ontologies to model the navigational structure, the compositional structure, and the user interfaces of data-intensive web sites, and provides a suit of tools to support site generation, maintenance, and personalization.

Formative work by Lave and Wenger has articulated how practices emerge through the interplay of informal processes with symbolic codifications and artifacts. In this paper, we describe how ontologies can serve as symbolic tools within a community of practice supporting communication and knowledge sharing. We show that when a community's perspective on an issue is stable, it opens the possibility for introducing knowledge services, based on an ontology co-constructed by knowledge engineers with stakeholders. Using a case study we describe our approach, ontology driven document enrichment, looking at how ontology construction and population can be supported by web based technologies.

Integrating working and learning is seen as a desirable alternative to traditional training regimes. An integrated approach to working and learning is more gradual, contextual, problem oriented and cost effective. Knowledge technology aims to catalyze workplace learning, but requires the right organisational culture and brings additional costs regarding the articulation, representation and transmission of knowledge. Our approach reduces these costs by making articulation a natural part of collaborative working, designing for both informal and formal knowledge, and facilitating the transition of socially situated knowledge through enriched documents. To be successful, our approach has certain prequesites concerning organisational culture, and the nature of shared documents, organisational knowledge and work activities.

Engineering design is a complex activity, relying heavily on know-how gained from personal experience. Competitive pressures and new technology are making further demands on the skills and experience of designers, as effective knowledge reuse in design is seen as increasingly vital, and the work of design teams is often a collaborative and distributed activity. University students with a thorough knowledge of the engineering domain can be ill prepared for professional practice, with its increasing reliance on skills and know-how as well as knowledge of theory. Our approach aims to better prepare students for professional practice, through hands-on experience of design reuse, participation in distributed collaboration, and the development of presentation and documentation skills. Our case-study in the domain of modelling engineering systems, in which the course materials themselves are evolving and distributed, has ramifications for the publication model of educational materials, and the way students should be prepared for working life.

The knowledge engineer is only weakly supported at three critical stages in the knowledge engineering life cycle: (1) knowledge acquisition during which problem conceptualization must largely be tackled with paper and pencil; (2) knowledge encoding, during which it is frequently necessary to be able to navigate across a variety of knowledge representation formalisms; and (3) large-scale debugging, in which the graphical rule traces cannot cope with enormous rule sets involving hundreds or thousands of rules. The research described attempts to provide just such support through complementary visual programming (VP) and program visualization (PV) techniques embedded in a fully implemented software environment called KEATS: the knowledge engineer's assistant. Several novel visual programming and program visualization techniques aimed at knowledge engineers have been developed, which include (1) a hypertext transcript analyzer from which conceptual models can be generated, (2) a direct graph manipulation sketchpad which allows the knowledge engineer to sketch out objects and relations (including control flow and rule dependencies) from which code can be generated, and (3) dependency viewers which allow the knowledge engineer to examine and manipulate temporal and logical rule dependencies at different levels of granularity. How these facilities are incorporated into KEATS and the key themes that emerge from this approach to visual knowledge engineering are discussed.>