C
Chris Newell
Researcher at BBC Research & Development
Publications - 8
Citations - 795
Chris Newell is an academic researcher from BBC Research & Development. The author has contributed to research in topics: Recommender system & User experience design. The author has an hindex of 3, co-authored 7 publications receiving 643 citations.
Papers
More filters
Journal ArticleDOI
Explaining the user experience of recommender systems
TL;DR: This paper proposes a framework that takes a user-centric approach to recommender system evaluation that links objective system aspects to objective user behavior through a series of perceptual and evaluative constructs (called subjective system aspects and experience, respectively).
Journal ArticleDOI
Updatable, Accurate, Diverse, and Scalable Recommendations for Interactive Applications
TL;DR: A novel graph vertex ranking recommendation algorithm called RP3β that reranks items based on three-hop random walk transition probabilities is presented that provides accurate recommendations with high long-tail item frequency at the top of the recommendation list and is extended for online updates at interactive speeds.
Proceedings ArticleDOI
Blockbusters and Wallflowers: Accurate, Diverse, and Scalable Recommendations with Random Walks
TL;DR: A novel graph vertex ranking recommendation algorithm called RP^3_beta is presented that re-ranks items based on 3-hop random walk transition probabilities and empirically, it is shown that this algorithm provides accurate recommendations with high long-tail item frequency at the top of the recommendation list.
Proceedings ArticleDOI
Design and evaluation of a client-side recommender system
Chris Newell,Libby Miller +1 more
TL;DR: This demonstration presents an alternative approach where major parts of the recommender system are implemented in scripts run by the user's client system.
Proceedings Article
Keyword-Based TV Program Recommendation.
Christian Wartena,Wout Slakhorst,Martin Wibbels,Zeno Gantner,Christoph Freudenthaler,Chris Newell,Lars Schmidt-Thieme +6 more
TL;DR: It is argued that a nearest-neighbor approach relying on unrestricted keywords deserves a special definition of similarity that also takes word similarities into account, and that rating predictions are significantly better if they do not only take into account the overlap of keywords between two documents, but also the mutual similarities between keywords.