This paper describes the use of Intelligent Agents and Ontologies to implement knowledge navigation and learner choice when interacting with complex information locations. The paper is in two parts: the first looks at how Agent Based Semantic Technology can be used to give users a more personalised experience as an individual. The paper then looks to generalise this technology to allow users to work with agents in hybrid group scenarios. In the context of University Learners, the paper outlines how we employ an Ontology of Student Characteristics to personalise information retrieval specifically suited to an individual’s needs. Choice is not a simple “show me your hand and make me a match” but a deliberative artificial intelligence (AI) that uses an ontologically informed agent society to consider the weighted solution paths before choosing the appropriate best. The aim is to enrich the student experience and significantly re-route the student’s journey. The paper uses knowledge-level interoperation of agents to personalise the learning space of students and deliver to them the information and knowledge to suite them best. The aim is to personalise their learning in the presentation/format that is most appropriate for their needs. The paper then generalises this Semantic Technology Framework using shared vocabulary libraries that enable individuals to work in groups with other agents, which might be other people or actually be AIs. The task they undertake is a formal assessment but the interaction mode is one of informal collaboration. Pedagogically this addresses issues of ensuring fairness between students since we can ensure each has the same experience (as provided by the same set of Agents) as each other and an individual mark may be gained. This is achieved by forming a hybrid group of learner and AI Software Agents. Different agent architectures are discussed and a worked example presented. The work here thus aims at fulfilling the student’s needs both in the context of matching their needs but also in allowing them to work in an Agent Based Synthetic Group. This in turn opens us new areas of potential collaborative technology. Details
Brayshaw M., Nganji J., Gordon N. (2017) Collaborative Hybrid Agent Provision of Learner Needs Using Ontology Based Semantic Technology. In: Zaphiris P., Ioannou A. (eds) Learning and Collaboration Technologies. Technology in Education. LCT 2017. Lecture Notes in Computer Science, vol 10296. Springer, Cham
People with visual impairments, particularly blind people face a lot of difficulties browsing the web with assistive technologies such as screen readers, when websites do not conform to accessibility standards and are thus inaccessible. HTML is the basic language for website design but its ALT attribute on the IMG element does not adequately capture comprehensive image semantics and description in a way that can be accurately interpreted by screen readers, hence blind people do not usually get the complete description of the image. Most of the problems however arise from web designers and developers not including a description of an image or not comprehensively describing these images to people with visual impairments. In this paper, we propose the use of the Image Description Assessment Tool (IDAT), a Java-based tool containing some proposed heuristics for assessing how well an image description matches the real content of the image on the web. The tool also contains a speech interface which can enable a visually impaired individual to listen to the description of an image that has been uploaded unto the system.
Nganji, J.T., Brayshaw, M., and Tompsett, B. (2013). Describing and Assessing Image Descriptions for Visually Impaired Web Users with IDAT, In 3rd International Conference on Intelligent Human Computer Interaction, Springer-Verlag, Lecture Notes in Computer Science, August 2011, reprinted in Advances in Intelligent Systems and Computing, Volume 179, Springer Verlag, 2013, pp 27-37, ISSN: 2194-5357 (Print) 2194-5365 (Online). [Link to article] [Link to PDF]
The increasing use of technology to enhance learning means both disabled students and higher education institutions face the challenge of adapting technology to meet the educational and special needs of students. As most e-learning systems are not designed to meet special needs, it is imperative to look for newer ways of designing e-learning systems to ensure that they are disability-aware and meet their assistive technology needs. In this light, this paper summarizes the result of research to seek better ways of enhancing learning for disabled students. Here, the resultant ONTODAPS system is introduced, including the methodology developed to design the system, its architecture and evaluation by 30 disabled students. The results of the usability evaluation are presented and discussed. It is hoped that researchers, instructional designers and developers of e-learning systems would look to this paper to gain insight into the design and development of disability-aware e-learning systems that will ensure that they are both accessible and usable to disabled students.
Nganji, J.T. and Brayshaw, M. (2014). Designing and reflecting on disability-aware e-learning systems: the case of ONTODAPS. The 14th IEEE International Conference on Advanced Learning Technologies- ICALT2014, July 7-9, Athens, Greece, pp.571-575.[Link to article] [Link to PDF]
The exploration of social artifacts for the disabled is an important and timely issue. The affordances of new technologies like the Semantic Web allow more intelligent handling of educational learning resources that open up the potential of personalisation of services to individuals. Contemporary legislation calls for “reasonable adjustments” and “reasonable accommodation” to be made to services in order to accommodate the needs of disabled people. Here, the authors examine, from a design perspective, how this might be done in the context of higher education. Specifically, they advocate a design based upon an ontology-based personalisation of learning resources to deliver to students’ real needs. To this end, so far little effort has been directed towards disabled students in higher education. The authors note some of the problems and issues with online assistive/adaptive technologies and propose a methodological fix. Here, they propose an ontology-based methodology for a Semantic Web community of agents that personalises learning resources to disabled students in higher education, specifically highlighting a disability-aware Semantic Web agency development methodology. The authors also present the results of usability evaluation of the implemented visual interface with some disabled and non-disabled students.
Nganji, J.T. and Brayshaw, M. (2013). Designing Personalised Learning Resources for Disabled Students Using an Ontology-Driven Community of Agents. In P. Isaias, & M. Baptista Nunes (Eds.), Information Systems Research and Exploring Social Artifacts: Approaches and Methodologies (pp. 81-102). Hershey, PA: Information Science Reference. doi:10.4018/978-1-4666-2491-7.ch00. [Link to Book Chapter]
Existing virtual learning environments (VLEs) in educational institutions are not designed with the expectation that students with disabilities will use them. Consequently, retrieving relevant information by some students with disabilities is a challenging task. The focus of this study was to propose the design of VLEs to incorporate ontologies that facilitate information retrieval by students with disabilities in their learning, thus serving as a semantic web-based assistive technology in education. An Ontology-Driven Disability-Aware Personalised E-Learning System (ONTODAPS) was designed and then used to recommend specific learning materials to learners based on their learning goal and disability type. Preliminary results of the evaluation of ONTODAPS, by 30 students with disabilities, indicate that 70% of the participants found ONTODAPS to offer a better personalisation, better access to learning materials (68%) and is easier to use (63%) in retrieving learning materials than Sakai. Thus ONTODAPS serves as an assistive tool in their education through retrieval of relevant learning materials in a suitable format which is compatible with their disability.
Nganji, J.T., Brayshaw, M. (2015). Facilitating Learning Resource Retrieval for Students with Disabilities through an Ontology- Driven and Disability-Aware Virtual Learning Environment. International Journal of Information Retrieval Research (IJIRR), Volume 5, Issue 3, pp. 75-98. [Link to Article]
The number of students with disabilities in UK higher education institutions increases every year. Delivering education online is becoming increasingly challenging as institutions encounter some disabilities requiring adjustments of learning environments. The law requires that people with disabilities be given equivalent learning experiences to their non-disabled peers through “reasonable adjustments”. Educational institutions have thus utilised assistive technologies to assist disabled students in their learning, but some of these technologies are incompatible with some learning environments, hence excluding some disabled students and resulting in a disability divide. To solve this problem, amongst other solutions, e-learning personalisation has been used and more recently, this is also achieved using Semantic Web technologies such as ontologies. Nevertheless, as ontologies are incorporated into learning environments little seems to be done to personalise learning for some disabled students. This study, in order to bridge the gap, proposes a personalisation approach based on a disability ontology containing information on various disabilities encountered in higher education, which can be used to present disabled students with learning resources relevant and suitable for their specific needs.
Nganji, J.T., Brayshaw, M. and Tompsett, B. (2011). Ontology-Based E-Learning Personalisation for Disabled Students in Higher Education. Innovation in Teaching and Learning in Information and Computer Sciences, Volume 10, Issue 1, pp. 1-11. [Link to article]
Purpose - The purpose of this paper is to show how personalisation of learning resources and services can be achieved for students with and without disabilities, particularly responding to the needs of those with multiple disabilities in e-learning systems. The paper aims to introduce the ONTODAPS e-learning system which has the mechanism for such personalisation.Design/methodology/approach - This paper reviews current e-learning systems that provide personalisation for students, including their strengths and weaknesses. The paper presents personalisation and its techniques and then presents ONTODAPS which is an ontology-driven and disability-aware e-learning system which personalises learning resources and services to students. Three case studies are considered to show how personalisation is achieved using ONTODAPS.Findings - This paper shows that it is possible to use automated ontology-based agents intercommunicating to provide an effective personalisation for disabled students. The results reveal that ONTODAPS is flexible enough to provide enough control and freedom to drive their learning. The results also suggest that ONTODAPS has the ability to provide appropriate levels of learner control by allowing them to self-direct learning through personalising learning resources and then allowing them to choose which resources they wish to access. This thus gives them a sense of ownership and control.Research limitations/implications - This research reveals that it is possible for e-learning systems to personalise learning for users with multiple disabilities. Thus, by considering the needs of such users and consulting them in the design and development process, developers of e-learning systems can produce systems that are both accessible and usable to students with disabilities.
Nganji, J.T., Brayshaw, M. and Tompsett, B. (2013). Ontology-Driven Disability-Aware E-Learning Personalisation with ONTODAPS. Campus Wide Information Systems, Volume 30, Issue 1, pp. 17-34. [Link to article] [Link to PDF]
Current efforts towards including students with disabilities in web-based higher education are well established. However, existing learning environments are not fully inclusive, particularly for those with multiple disabilities. Most learning environments built for students with disabilities limit themselves to meeting the needs of specific disabilities and do not attempt to scale up to the difficulties of designing for those with multiple disabilities. This paper seeks to address how virtual learning environments (VLEs) can be designed to include the needs of learners with multiple disabilities. Specifically, it employs AI to show how specific learning materials from a huge repository of learning materials can be recommended to learners with various disabilities. This is made possible through employing semantic web technology to model the learner and their needs. Three techniques are discussed to combine requirements. Simple logical operators, knowledge based rules, and machine learning based rule induction are combined in this integrated approach. It is hoped that developers of e-learning systems will be encouraged from this approach to design fully inclusive virtual learning environments.
Nganji, J.T. and Brayshaw, M. (2015). Personalizing Learning Materials for Students with Multiple Disabilities in Virtual Learning Environments. Science and Information Conference 2015- SAI2015, July 28-30, London, UK, pp. 69-76. [Link to article]
Disability legislations such as the Disability Discrimination Act 1995, 2005 and Americans with Disabilities Act 1990 call on service providers to make “reasonable adjustments” and “reasonable accommodation” respectively to their services in order to accommodate the needs of disabled people. Higher education institutions as service providers can respond through their services. Nevertheless, there is an increasing challenge in using digital media to deliver services due to the numerous problems associated with inaccessibility of some online systems with assistive/adaptive technologies. Personalisation is a solution to such problems as it provides content to students based on their needs. However, very little of such personalisation has been targeted towards disabled students and hence, this paper proposes an ontology approach for a semantic web community of agents that personalises services to disabled students in higher education. We present the architecture of such an agency, including a disability-aware semantic web agency development methodology and also present the ADOOLES ontology employed for such personalisation.
Nganji, J.T., and Brayshaw, M. (2011). Towards an Ontology-Based Community of Agents for Personalisation of Services for Disabled Students. In: Blashki, K. (Ed.). Proceedings of the IADIS International Conference Interfaces and Human Computer Interaction (IHCI 2011), 24-26 July 2011, Rome, Italy, pp. 193-200. [Link to article PDF]