Mark J. Weal

Automatic ontology-based knowledge extraction from Web documents

To bring the Semantic Web to life and provide advanced knowledge services, we need efficient ways to access and extract knowledge from Web documents. Although Web page annotations could facilitate such knowledge gathering, annotations are rare and will probably never be rich or detailed enough to cover all the knowledge these documents contain. Manual annotation is impractical and unscalable, and automatic annotation tools remain largely undeveloped. Specialized knowledge services therefore require tools that can search and extract specific knowledge directly from unstructured text on the Web, guided by an ontology that details what type of knowledge to harvest. An ontology uses concepts and relations to classify domain knowledge. Other researchers have used ontologies to support knowledge extraction, but few have explored their full potential in this domain. The paper considers the Artequakt project which links a knowledge extraction tool with an ontology to achieve continuous knowledge support and guide information extraction. The extraction tool searches online documents and extracts knowledge that matches the given classification structure. It provides this knowledge in a machine-readable format that will be automatically maintained in a knowledge base (KB). Knowledge extraction is further enhanced using a lexicon-based term expansion mechanism that provides extended ontology terminology.

Ubi-learning integrates indoor and outdoor experiences

Digital augmentation dissolves many of the physical barriers to learning by offering tools to integrate data and discoveries that travel with students as they explore new terrain.

Ambient wood: designing new forms of digital augmentation for learning outdoors

Ubiquitous and mobile technologies provide opportunities for designing novel learning experiences that move out of the classroom. Information can be presented and interacted with in a variety of ways while exploring a physical environment. A key issue this raises is when, where, what and how much? Our research is concerned with the design, delivery and interaction of digital information when learning about ecology outdoors. We present a framework of the different forms of digital augmentation and the different processes by which they can be accessed. Using the framework, we designed an outdoors learning experience, aimed at encouraging students to carry out contextualized scientific enquiry and to reflect on their interactions. Pairs of 11-12 year olds explored a woodland and were presented at certain times with different forms of digital augmentation. Our study showed that this kind of exploration promoted interpretation and reflection at a number of levels of abstraction.

Auld Leaky: A Contextual Open Hypermedia Link Server

The work of the Open Hypermedia Systems Working Group (OHSWG) has lead to the creation of several hypermedia models and a common protocol for Navigational Hypertext. However none of these include a working model of context. In this paper we present how we have extended the Fundamental Open Hypermedia Model (FOHM) to include context and behaviour. We then present Auld Leaky, a lightweight contextual link server that stores and serves structures represented in FOHM, using Context to filter query results.

An unsupervised training method for non-intrusive appliance load monitoring☆

Abstract Non-intrusive appliance load monitoring is the process of disaggregating a households total electricity consumption into its contributing appliances. In this paper we propose an unsupervised training method for non-intrusive monitoring which, unlike existing supervised approaches, does not require training data to be collected by sub-metering individual appliances, nor does it require appliances to be manually labelled for the households in which disaggregation is performed. Instead, we propose an approach which combines a one-off supervised learning process over existing labelled appliance data sets, with an unsupervised learning method over unlabelled household aggregate data. First, we propose an approach which uses the Tracebase data set to build probabilistic appliance models which generalise to previously unseen households, which we empirically evaluate through cross validation. Second, we use the Reference Energy Disaggregation Data set to evaluate the accuracy with which these general models can be tuned to the appliances within a specific household using only aggregate data. Our empirical evaluation demonstrates that general appliance models can be constructed using data from only a small number of appliances (typically 3–6 appliances), and furthermore that 28–99% of the remaining behaviour which is specific to a single household can be learned using only aggregate data from existing smart meters.

Towards Open Adaptive Hypermedia

Research at the University of Southampton has extended generalised Open Hypermedia (OH) models to include concepts of context and behaviour, both traditionally very important to the Adaptive Hypermedia (AH) domain. In this paper we re-evaluate Brusilovskys pragmatic taxonomy of AH techniques from a structural perspective. A variety of OH structures are discussed that can be used to implement the techniques found in the taxonomy. By identifying common structures we gain a new perspective on the relationship between different AH techniques.

The ambient wood journals: replaying the experience

The Ambient Wood project aims to facilitate a learning experience using an adaptive infrastructure in an outdoor environment. This involves sensor technology, virtual world orchestration, and a wide range of devices ranging from hand-held computers to speakers hidden in trees.Whilst performing user trials of the Wood, the activities of children participating in the experiments were recorded in detailed log files. An aim of the project has been to replay these log files using adaptive hypermedia techniques to enable the children to further reflect on their experience back in the classroom environment.

Semantic Technologies for Learning and Teaching in the Web 2.0 Era

Deploying semantic tools and services over a field of linked data could be a way to address many current challenges of higher education. The strengths of semantic technologies for learning and teaching, and their benefits for digital libraries, virtual communities, and e-learning, have been a major topic of discussion during recent years. Experts argue that semantic technologies can enhance the advanced learning experience by using the expressive power of metadata to describe learning content, people, and services, and then matching these intelligently.

The literacy fieldtrip: using UbiComp to support children's creative writing

Fieldtrips, traditionally associated with science, history and geography teaching, have long been used to support childrens learning by allowing them to engage with environments first-hand. Recently, ubiquitous computing (UbiComp) has been used to enhance fieldtrips in these educational areas by augmenting environments with a range of instruments, devices and sensors. However, the sorts of interaction design that UbiComp makes possible have the potential not just to enhance the value of educational techniques in known application areas, but also to expand the application of those techniques into new areas of curriculum. We report on a UbiComp-supported fieldtrip to support creative writing, associated with the learning of literacy skills. We discuss how the fieldtrip, designed and run in the grounds of a historic English country house with Year 5 UK schoolchildren, engendered interactions which changed both the processes and products of creative writing, with benefits for both teachers and children.

Digital Futures? Sociological Challenges and Opportunities in the Emergent Semantic Web

In the context of recent debates about the ‘data deluge’ and the future of empirical sociology, this article turns attention to current activities aimed at achieving far-reaching transformations to the World Wide Web. The emergent ‘Semantic Web’ has received little attention in sociology, despite its potentially profound consequences for data. In response to more general recent calls for a critical politics of data we focus our enquiry as follows: first, we explore how sociological analysis of the artefacts and tools that are currently being developed to build a Semantic Web helps us to uncover the potential effects of this ‘next generation’ web on knowledge, data and expertise; and second we consider what a Semantic Web might offer to sociological research. We conclude by considering some implications of multidisciplinary engagement with the Web for the future of sociology.