User Modelling Research Papers - Academia.edu (original) (raw)

It is a widely held assumption that learning style is a useful model for quantifying user characteristics for effective personalized learning. We set out to challenge this assumption by discussing the current state of the art, in relation... more

It is a widely held assumption that learning style is a useful model for quantifying user characteristics for effective personalized learning. We set out to challenge this assumption by discussing the current state of the art, in relation to quantitative evaluations of such systems and also the methodologies that should be employed in such evaluations. We present two case studies that provide rigorous and quantitative evaluations of learning-style-adapted e-learning environments. We believe that the null results of both these studies indicate a limited usefulness in terms of learning styles for user modeling and suggest that alternative characteristics or techniques might provide a more beneficial experience to users.

This paper describes user modelling in I-Help, a system to facilitate communication amongst learners. There are two I-Help components: Private and Public Discussions. In the Private Discussions learners take part in a one-on-one... more

This paper describes user modelling in I-Help, a system to facilitate communication amongst learners. There are two I-Help components: Private and Public Discussions. In the Private Discussions learners take part in a one-on-one interaction with a partner (possibly a peer). The Public Discussions are open - everyone in the group has access to all discussion forums relevant to that group.

User profiling techniques have mostly focused on retrieving and representing a user's knowledge, context and interests in order to provide recommendations, personalise search, and build user-adaptive systems. However, building a user... more

User profiling techniques have mostly focused on retrieving and representing a user's knowledge, context and interests in order to provide recommendations, personalise search, and build user-adaptive systems. However, building a user profile on a single social network limits the quality and completeness of the profile, especially when interoperability of the profile is key and its reuse on different sites is necessary for providing other types of personalisation. Indeed recent studies have shown that users on the Social Web often use different social networking sites for diverse, and sometimes non-overlapping, purposes and interests. In this paper, we describe our methodology for the automatic creation and aggregation of interoperable and multi-domain user profiles using semantic technologies. Moreover, we propose a user study on different user profiling techniques for social networking websites in general, and for Twitter and Facebook in particular. In this regard, based on the results of our user evaluation, we investigate (i) the accuracy of different methodologies for profiling, (ii) the effect of time decay functions on ranking user interests, and (iii) the benefits of merging different user models using semantic technologies.

... the interaction process, ie the control of the cursor and the haptic output, we have built a specialized 'multimodal mouse' with ... The system architecture should be modular and flexible in order to support the integration... more

... the interaction process, ie the control of the cursor and the haptic output, we have built a specialized 'multimodal mouse' with ... The system architecture should be modular and flexible in order to support the integration of other modal-ities and ... Figure 7: The multi-agent architecture ...

Personalised information systems (PISs), related to different fields (travelling and mobility, production, logistics and so on), represent an object of many research and development perspectives. Using PISs, it becomes possible to supply... more

Personalised information systems (PISs), related to different fields (travelling and mobility, production, logistics and so on), represent an object of many research and development perspectives. Using PISs, it becomes possible to supply the user only with the pertinent information that suits their preferences. Indeed, thanks to personalisation, the user may feel that a particular PIS is developed for them. This system adaptation becomes a necessity for the user's satisfaction. In this context, many studies were orientated toward the user modelling, the design methods of PIS and the personalisation algorithms, etc. but, the evaluation of these systems is neglected. Difficulties concerning context-centred evaluation appear. This paper is focused on the evaluation of the personalised information systems in order to optimise the personalisation quality according to several criteria. For such systems, it is important to envisage new adapted evaluation methods. An evaluation method using a PIS simulation model, called MetSim (Method evaluation per Simulation), is proposed. MetSim is also based on the case-based reasoning system to identify problems. This evaluation approach has been validated by applying it to assess PISs in the logistics field.

Intelligent agents can play a pivotal role in providing both software systems and augmented interfaces, to individual users from all walks of life, to utilise the Internet 24 h a day, 7 days a week (24×7), including interaction with other... more

Intelligent agents can play a pivotal role in providing both software systems and augmented interfaces, to individual users from all walks of life, to utilise the Internet 24 h a day, 7 days a week (24×7), including interaction with other users, over both wireless and broadband infrastructures. However, traditional approaches to user modelling are not adequate for this purpose, as they mainly account for a generic, approximate, idealised user. New user models are therefore required to be adaptable for each individual and flexible enough to represent the diversity of all users using information technology. Such models should be able to cover all aspects of an individual’s life—those aspects of most interest to the individual user themselves. This paper describes a novel intelligent agent architecture and methodology both called ShadowBoard, based on a complex user model drawn from analytical psychology. An equally novel software tool, called the DigitalFriend based on ShadowBoard, is also introduced. This paper illustrates how aspects of user cognition can be outsourced, using, for example, an internationalised book price quoting agent. The Locales Framework from Computer Supported Co-operative Work is then used to understand the problematic aspects of interaction involved in complex social spaces, identifying specific needs for technology intervention in such social spaces, and to understand how interactions amongst mobile users with different abilities might be technically assisted in such spaces. In this context, the single user-centred multi-agent technology demonstrated in the DigitalFriend is adapted to a multi-user system dubbed ShadowPlaces. The aim of ShadowPlaces is to outsource some of the interaction necessary, for a group of mobile individuals with different abilities to interact cooperatively and effectively in a social world, supported by wireless networks and backed by broadband Internet services. An overview of the user model, the architecture and methodology (ShadowBoard) and the resulting software tool (the DigitalFriend) is presented, and progress on ShadowPlaces—the multi-user version—is outlined.

Cultural heritage management is a multiple-perspective enterprise where several disciplines and practices contribute to successful dissemination and communication. Digital data in support of cultural heritage management are addressed by... more

Cultural heritage management is a multiple-perspective enterprise where several disciplines and practices contribute to successful dissemination and communication. Digital data in support of cultural heritage management are addressed by the digital curation process, which has been emerging to account for the diversity of disciplinary communities and cultural heritage organizations. Digital curation addresses the diversity of participating skills and practices by working on the relationship between the cultural heritage objects and their digital counterparts. In particular, the innumerable initiatives for providing access to cultural heritage data are ideally coordinated by digital curation and are part of the process since the beginning. However, some thorough reflections on its role and implementation in cultural heritage institutions yet lack. In this paper, we provide a survey of the digital curation process, by unpacking the component curatorial tasks, with the solutions that have been proposed in the literature and in the application projects to account for the multiple perspectives at hand. CCS CONCEPTS • Human-centered computing → Collaborative interaction; Human computer interaction (HCI); • Information systems → Data management systems; Digital libraries and archives; • Social and professional topics → Management of computing and information systems. KEYWORDS digital curation; cultural heritage; interdisciplinary process; project workflow ACM Reference Format:

With the rapid growth in users on social networks, there is a corresponding increase in user-generated content, in turn resulting in information overload. On Twitter, for example, users tend to receive uninterested information due to... more

With the rapid growth in users on social networks, there is
a corresponding increase in user-generated content, in turn resulting in information overload. On Twitter, for example, users tend to receive uninterested information due to their non-overlapping interests from the people whom they follow. In this paper we present a Semantic Web approach to filter public tweets matching interests from personalized user profiles. Our approach includes automatic generation of multi-domain and personalized user profiles, filtering Twitter stream based on the generated profiles and delivering them in real-time. Given that users interests and personalization needs change with time, we also discuss how our application can adapt with these changes.