Now showing 1 - 10 of 149
  • Publication
    The experience web : a case-based reasoning perspective
    With the rise of user-generated content (blogs, wikis, ratings, reviews, opinions etc.) the web is evolving from a repository of content into a repository of experiences. And as it evolves there are many opportunities to harness these experiences. In this paper we consider some of the challenges associated with harnessing online experiences by adopting a case-based reasoning perspective, and highlighting how existing case-based approaches might be adapted to take advantage of this new world of the experience web.
      1194
  • Publication
    Collaboration and reputation in social web search
    Recent research has highlighted the inherently collaborative nature of many Web search tasks, even though collaborative searching is not supported by mainstream search engines. In this paper, we examine the activity of early adopters of HeyStaks, a collaborative Web search framework that is designed to complement mainstream search engines such as Google, Bing, and Yahoo. The utility allows users to search as normal, using their favourite search engine, while benefiting from a more collaborative and social search experience. HeyStaks supports searchers by harnessing the experiences of others, in order to enhance organic mainstream result-lists. We review some early evaluation results that speak to the practical benefits of search collaboration in the context of the recently proposed Reader-to-Leader social media analysis framework [11]. In addition, we explore the idea of utilising the reputation model introduced by McNally et al.[6] in order to identify the search leaders in HeyStaks, i.e. those users who are responsible for driving collaboration in the HeyStaks application.
      1888
  • Publication
    Sticking with a Winning Team: Better Neighbour Selection for Conversational Collaborative Recommendation
    Conversational recommender systems have recently emerged as useful alternative strategies to their single-shot counterpart, especially given their ability to expose a user’s current preferences. These systems use conversational feedback to hone in on the most suitable item for recommendation by improving the mechanism that finds useful collaborators. We propose a novel architecture for performing recommendation that incorporates information about the individual performance of neighbours during a recommendation session, into the neighbour retrieval mechanism. We present our architecture and a set of preliminary evaluation results that suggest there is some merit to our approach.We examine these results and discuss what they mean for future research.
      82
  • Publication
    The case-based experience web
    With the rise of user-generated content (blogs, wikis, ratings, reviews, opinions etc.) the web is evolving from a repository of content into a repository of experiences, and as it evolves there are many opportunities to harness these experiences. In this paper we consider some of the challenges associated with harnessing online experiences by adopting a case-based reasoning perspective, and highlighting how existing case-based approaches might be adapted to take advantage of this new world of the experience web. To make this discussion more concrete we will draw on examples from one recent case-based attempt to harness the experiences of communities of users in the area of web search.
      618
  • Publication
    Distortion as a validation criterion in the identification of suspicious reviews
    (University College Dublin. School of Computer Science and Informatics, 2010-05-02) ; ; ;
    Assessing the trustworthiness of reviews is a key issue for the maintainers of opinion sites such as TripAdvisor. In this paper we propose a distortion criterion for assessing the impact of methods for uncovering suspicious hotel reviews in TripAdvisor. The principle is that dishonest reviews will distort the overall popularity ranking for a collection of hotels. Thus a mechanism that deletes dishonest reviews will distort the popularity ranking significantly, when compared with the removal of a similar set of reviews at random. This distortion can be quantified by comparing popularity rankings before and after deletion, using rank correlation. We present an evaluation of this strategy in the assessment of shill detection mechanisms on a dataset of hotel reviews collected from TripAdvisor.
      1045
  • Publication
    A Distributed Asynchronous Deep Reinforcement Learning Framework for Recommender Systems
    In this paper we propose DADRL, a distributed, asynchronous reinforcement learning recommender system based on the asynchronous advantage actor-critic model (A3C), which combines ideas from A3C and federated learning (FL). The proposed algorithm keeps the user preferences or interactions on local devices and uses a combination of on-device, local recommendation models and a complementary global model. The global model is trained only by the loss gradients of the local models, rather than directly using user preferences or interactions data. We demonstrate, using well-known datasets and benchmark algorithms, how this approach can deliver performance that is comparable with the current state-of-the-art while enhancing user privacy.
      267
  • Publication
    Personalized, Health-Aware Recipe Recommendation: An Ensemble Topic Modeling Based Approach
    Food choices are personal and complex and have a significant impact on our long-term health and quality of life. By helping users to make informed and satisfying decisions, Recommender Systems (RS) have the potential to support users in making healthier food choices. Intelligent users-modeling is a key challenge in achieving this potential. This paper investigates Ensemble Topic Modelling (EnsTM) based Feature Identification techniques for efficient user-modeling and recipe recommendation. It builds on findings in EnsTM to propose a reduced data representation format and a smart user-modeling strategy that makes capturing user-preference fast, efficient and interactive. This approach enables personalization, even in a cold-start scenario. We compared three EnsTM based variations through a user study with 48 participants, using a large-scale, real-world corpus of 230,876 recipes, and compare against a conventional Content Based (CB) approach. EnsTM based recommenders performed significantly better than the CB approach. Besides acknowledging multi-domain contents such as taste, demographics and cost, our proposed approach also considers user’s nutritional preference and assists them finding recipes under diverse nutritional categories. Furthermore, it provides excellent coverage and enables implicit understanding of user’s food practices. Subsequent analysis also exposed correlation between certain features and healthier lifestyle.
      57
  • Publication
    Garment-based body sensing using foam sensors
    Wearable technology is omnipresent to the user. Thus, it has the potential to be significantly disruptive to the user’s daily life. Context awareness and intuitive device interfaces can help to minimize this disruption, but only when the sensing technology itself is not physically intrusive: i.e., when the interface preserves the user’s homeostatic comfort. This work evaluates a novel foambased sensor for use in body-monitoring for contextaware and gestural interfaces. The sensor is particularly attractive for wearable interfaces due to its positive wearability characteristics (softness, pliability, washability), but less precise than other similar sensors. The sensor is applied in the garment-based monitoring of breathing, shoulder lift (shrug), and directional arm movement, and its accuracy is evaluated in each application. We find the foam technology most successful in detecting the presence of movement events using a single sensor, and less successful in measuring precise, relative movements from the coordinated responses of multiple sensors. The implications of these results are considered from a wearable computing perspective.
      301
  • Publication
    Using social ties in group recommendation
    (Intelligent Systems Research Centre, 2011-08-31) ; ;
    The social web is a mass of activity, petabytes of data are generated yearly. The social web has proven to be a great resource for new recommender system techniques and ideas. However it would appear that typically these techniques are not so social, as they only generate recommendations for a user acting alone. In this paper we take the social graph data and preference content (via Facebook) of 94 user study participants and generate social group recommendations for them and their friends. We evaluate how different aggregation policies perform in deciding the final group recommendation. Our findings show that in an offline evaluation an aggregation policy which takes into consideration social weighting outperforms other aggregation policies.
      718
  • Publication
    Explanation-based Ranking in Opinionated Recommender Systems
    (CEUR Workshop Proceedings, 2018-09-21) ; ;
    Explanations can help people to make better choices, but their use in recommender systems has so far been limited to the annotation of recommendations after they have been ranked and suggested to the user. In this paper we argue that explanations can also be used to rank recommendations. We describe a technique that uses the strength of an item’s explanation as a ranking signal – preferring items with compelling explanations – and demonstrate its efficacy on a real-world dataset.
      129