Now showing 1 - 10 of 26
  • 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.
  • Publication
    Mining Experiential Product Cases
    Case-based reasoning (CBR) attempts to reuse past experiences to solve new problems. CBR ideas are commonplace in recommendation systems, which rely on the similarity between product queries and a case base of product cases. But, the relationship between CBR and many of these recommenders can be tenuous: the idea that product cases made up of static meta-data type features are experiential is a stretch; unless one views the type of case descriptions used by collaborative filtering (user ratings across products) as experiential. Here we explore and evaluate how to automatically generate product cases from user-generated reviews to produce cases that are based on genuine user experiences for use in a case-based product recommendation system.
  • Publication
    UP-TreeRec: Building dynamic user profiles tree for news recommendation
    Online News recommendation systemsaim to address the information explosion of news and make personalized recommendation for users. The key problem of personalized news recommendation is to model users’ interests and track their changes. A common way to deal with usermodeling problem is to build user profiles from observed behavior. However, the majority of existing methods make static representation to user profiles and little research has focused on the effective user modeling that could dynamically capture user interests in news topics.To address this problem, in this paper, we propose UP-TreeRec, a news recommendation framework based on user profile tree (UP-Tree), which is a novel framework combining content-based and collaborative filtering techniques. First, by exploitinga novel topic model namely UI-LDA, we obtain the representationvectorsfor news content in topic spaceas the fundamentalbridgeto associate user interests with news topics. Next, we design a decision tree with a dynamically changeable structure to construct a user interest profile from his feedback. Furthermore, we present a clustering based multidimensional similarity computation method to select the nearest neighbor of UP-Treeefficiently. We also provide a Map-Reduce framework based implementation that enables scaling our solution to real-world news recommendation problems.We conducted several experiments compared to the state-of-the-art approaches on real-world datasets and the experimental results demonstrate that our approach significantly improves the accuracy and effectiveness in news recommendation.
      162Scopus© Citations 10
  • Publication
    Pseudo-labelling Enhanced Media Bias Detection
    Leveraging unlabelled data through weak or distant supervision is a compelling approach to developing more effective text classification models. This paper proposes a simple but effective data augmentation method, which leverages the idea of pseudo-labelling to select samples from noisy distant supervision annotation datasets. The result shows that the proposed method improves the accuracy of biased news detection models.
  • Publication
    Why I like it: Multi-task Learning for Recommendation and Explanation
    We describe a novel, multi-task recommendation model, which jointly learns to perform rating prediction and recommendation explanation by combining matrix factorization, for rating prediction, and adversarial sequence to sequence learning for explanation generation. The result is evaluated using real-world datasets to demonstrate improved rating prediction performance, compared to state-of-the-art alternatives, while producing effective, personalized explanations.
    Scopus© Citations 94  1592
  • Publication
    Opinionated Product Recommendation
    In this paper we describe a novel approach to case-based product recommendation. It is novel because it does not leverage the usual static, feature-based, purely similarity-driven approaches of traditional case-based recommenders. Instead we harness experiential cases, which are automatically mined from user generated reviews, and we use these as the basis for a form of recommendation that emphasises similarity and sentiment. We test our approach in a realistic product recommendation setting by using live-product data and user reviews.
    Scopus© Citations 42  703
  • Publication
    From More-Like-This to Better-Than-This: Hotel Recommendations from User Generated Reviews
    (ACM, 2016-07-17) ;
    To help users discover relevant products and items recommender systems must learn about the likes and dislikes of users and the pros and cons of items. In this paper, we present a novel approach to building rich feature-based user profiles and item descriptions by mining user-generated reviews. We show how this information can be integrated into recommender systems to deliver better recommendations and an improved user experience.
    Scopus© Citations 9  337
  • Publication
    Leveraging BERT to Improve the FEARS Index for Stock Forecasting
    Financial and Economic Attitudes Revealed by Search (FEARS) index reflects the attention and sentiment of public investors and is an important factor for predicting stock price return. In this paper, we take into account the semantics of the FEARS search terms by leveraging the Bidirectional Encoder Representations from Transformers (BERT), and further apply a self-attention deep learning model to our refined FEARS seamlessly for stock return prediction. We demonstrate the practical benefits of our approach by comparing to baseline works.
  • Publication
    Mining Features and Sentiment from Review Experiences
    Supplementing product information with user-generated content such as ratings and reviews can help to convert browsers into buyers. As a result this type of content is now front and centre for many major e-commerce sites such as Amazon. We believe that this type of content can provide a rich source of valuable information that is useful for a variety of purposes. In this work we are interested in harnessing past reviews to support the writing of new useful reviews, especially for novice contributors. We describe how automatic topic extraction and sentiment analysis can be used to mine valuable information from user-generated reviews, to make useful suggestions to users at review writing time about features that they may wish to cover in their own reviews. We describe the results of a live-user trial to show how the resulting system is capable of delivering high quality reviews that are comparable to the best that sites like Amazon have to offer in terms of information content and helpfulness.
      428Scopus© Citations 9
  • 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.