Now showing 1 - 10 of 157
  • Publication
    Passive Profiling from Server Logs in an Online Recruitment Environment
    The success of recommender systems ultimately depends on the availability of comprehensive user profiles that accurately capture the interests of endusers. However, the automatic compilation of such profiles represents a complex learning task. In this paper, we focus on how accurate user profiles can be generated directly from analysing the behaviours of Web users in the CASPER project. In CASPER user profiles are constructed by passively monitoring the click-stream and read-time behaviour of users. We will argue that building accurate profiles from such data is far from straightforward. In particular, we will describe the techniques that are used in CASPER to generate highquality graded user profiles from server logs. Finally, we will describe a comparative evaluation of these different techniques on real user data.
  • Publication
    A recommender system approach to enhance web search and query formulation
    While search engines are the primary means by which information is located online, significant issues remain when trying to satisfy the needs of searchers, especially in the face of the type of vague queries that dominate Web search. In this paper, we tackle this problem by applying a recommender system approach to Web search which allows users to dynamically interact with the result-space that is of interest to them. Our proposed recommendation interface also facilitates query expansion through a context-sensitive tag cloud, helping searchers to efficiently assimilate potential expansion terms that are mined from results of interest. We present findings from a live user trial of our approach which indicate, for example, that it facilitates users to locate relevant information more quickly when compared to using standard search engine result lists.
  • Publication
    Content on demand for fourth year advanced materials and manufacturing students
    (International Symposium of Engineering Education, 2012-07-18) ; ; ; ; ;
    There is growing recognition of the key role that social and informal learning play in Higher Education. There is also increasing interest in technologies that enable, capture and channel this type of learning to students at their point of need and personalised to their ability. The objective of this project was to leverage research technologies from the areas of adaptive hypermedia, social and semantic search to create an application to deliver learning resources to students tailored to their specific learning needs. In this project, some 130 digital learning resources, specific to a final year advanced materials and manufacturing module, were made available to the students via a Help Block plugin in the Moodle Virtual Learning Environment. The students were required to use the Help Block as a just-in-time learning resource to help them complete a continuous assessment assignment. The assignment required the students to select an advanced manufacturing process and associated material describing the manufacturing process steps, control and specifications and presenting the technological benefits of the process and material used relative to competing processes and materials. Post-trial, students were asked to complete a questionnaire to describe their experience with the Help Block in terms of whether it assisted them in completing the assignment, for example, and its ease of use. The system, evaluation findings, and some suggestions for future system enhancements are presented in the paper.
  • Publication
    The sensor web : bringing information to life
    (ERCIM EEIG, 2009-01)
    Keynote for the special theme: the Sensor Web
  • Publication
    Demonstrating social search a la HeyStaks
    For all the success of mainstream search engines there are a number of opportunities for improving on the conventional Web search user experience. In this short paper we consider the default assumption that search is solitary in nature, an isolated interaction between individual user and search engine. We highlight the value of a more collaborative approach to Web search and briefy present a novel add-on for mainstream search engines: HeyStaks ( It is designed to provide a more collaborative search experience, one in which recommendation technologies play a central role, by learning from the search experiences of groups of searchers in order to provide targeted recommendations during future search sessions.
  • Publication
    A comparison of a computer game-based exercise system with conventional approaches of exercise therapy in rheumatology patients
    There is a need to increase long-term exercise compliance amongst rheumatology patients to improve symptoms and quality of life. Exergaming systems, (computer video-game based exercise) could provide these patients with a motivating exercise tool to achieve such. This study aimed to compare the subjective reports of a group of rheumatology patients who exercised with an exergaming system to the reports of a similar group who performed the conventional, equivalent form of exercise, without the exergaming system.
  • Publication
    Recommender Systems: A Healthy Obsession
    (AAAI Press, 2019-07-23)
    We propose endurance sports as a rich and novel domain for recommender systems and machine learning research. As sports like marathon running, triathlons, and mountain biking become more and more popular among recreational athletes, there exists a growing opportunity to develop solutions to a number of interesting prediction, classification, and recommendation challenges, to better support the complex training and competition needs of athletes. Such solutions have the potential to improve the health and well-being of large populations of users, by promoting and optimising exercise as part of a productive and healthy lifestyle.
  • Publication
    Does TripAdvisor Makes Hotels Better?
    (University College Dublin. School of Computer Science and Informatics, 2010-12) ; ; ;
    It seems reasonable to expect that the emergence of opinion sites such as TripAdvisor should result in significant behavior changes among service providers. They might be expected to improve their service because disgruntled customers have the facility to share their impressions with a wider audience. There are two aspects to this, service providers are motivated to improve their services in order to avoid negative comment that can reach a wide audience and they are informed about what should be changed in order to improve their service. We report on an analysis of reviews relating to the hotel sector in Ireland that demonstrates this “TripAdvisor effect”. We compare these results with an analysis on Las Vegas hotels over a similar time period, where the effect is absent, presumably because sensitivity to reputation on TripAdvisor is already well-established there.
  • Publication
    Topic Extraction from Online Reviews for Classification and Recommendation
    Automatically identifying informative reviews is increasingly important given the rapid growth of user generated reviews on sites like Amazon and TripAdvisor. In this paper, we describe and evaluate techniques for identifying and recommending helpful product reviews using a combination of review features, including topical and sentiment information, mined from a review corpus.