Now showing 1 - 6 of 6
  • Publication
    The Ambient Calendar
    It is becoming difficult to convey information from an everincreasing number of digital sources to users in a condensed and meaningful way. This growth has particularly occurred with peripheral information sources. These are of general interest to users, but do no require or typically command constant focus or attention. Examples include weather, stock data, blogs, and calendars. Ambient Displays present information unobtrusively in an intelligent fashion using abstract visual cues and metaphors and have the possibility of acting as a complement to information filtering systems. We describe the implementation of an ambient display that contains elements representing time, weather, public transport departure times, and the proximity of friends. An initial impact study was undertaken and found a high sense of usefulness and curiosity in the finished application and in the field as a whole.
      923
  • Publication
    Using Twitter to recommend real-time topical news
    Recommending news stories to users, based on their preferences,has long been a favourite domain for recommender systems research. In this paper, we describe a novel approach to news recommendation that harnesses real-time micro-blogging activity, from a service such as Twitter, as the basis for promoting news stories from a user's favourite RSS feeds. A preliminary evaluation is carried out on an implementation of this technique that shows promising results.
      21022Scopus© Citations 323
  • Publication
    On using the real-time web for news recommendation & discovery
    In this work we propose that the high volumes of data on real-time networks like Twitter can be harnessed as a useful source of recommendation knowledge. We describe Buzzer, a news recommendation system that is capable of adapting to the conversations that are taking place on Twitter. Buzzer uses a content-based approach to ranking RSS news stories by mining trending terms from both the public Twitter timeline and from the timeline of tweets generated by a user’s own social graph (friends and followers). We also describe the result of a live-user trial which demonstrates how these ranking strategies can add value to conventional RSS ranking techniques, which are largely recency-based.
      1085Scopus© Citations 22
  • Publication
    Buzzer : online real-time topical news article and source recommender
    The significant growth of media and user-generated content online has allowed for the widespread adoption of recommender systems due to their proven ability to reduce the workload of a user and personalise content. In this paper, we describe our prototype system called Buzzer, which harnesses real-time micro-blogging activity, such as Twitter, as the basis for promoting personalised content, such as news articles, from RSS feeds. We also introduce several new features, that include a technique for recommending community articles from the pooled resources of all system users and also a mechanism for recommending source RSS feeds to which the user does not subscribe.
      3291Scopus© Citations 2
  • Publication
    Towards a Novel and Timely Search and Discovery System Using the Real-Time Social Web
    The world of web search is changing. Mainstream search engines like Google and Bing are adding social signals to conventional query-based services while social networks like Twitter and Facebook are adding query-based search to sharing-based services. Our search and discovery system, Yokie, harnesses the wisdom of the crowd of communities of Twitter users to create indexes of proto-content (or recently shared content) that is typically not yet indexed by mainstream search engines. The system includes an architecture [13] for a range of contextual queries and ranking strategies beyond standard relevance. In this paper, we focus on evaluating Yokies ability to retrieve timely, relevant and exclusive results with which users interacted and found useful, compared to other standard web services.
      257
  • Publication
    Terms of a feather : content-based news discovery and recommendation using Twitter
    User-generated content has dominated the web’s recent growth and today the so-called real-time web provides us with unprecedented access to the real-time opinions, views, and ratings of millions of users. For example, Twitter’s 200m+ users are generating in the region of 1000+ tweets per second. In this work, we propose that this data can be harnessed as a useful source of recommendation knowledge. We describe a social news service called Buzzer that is capable of adapting to the conversations that are taking place on Twitter to ranking personal RSS subscriptions. This is achieved by a content-based approach of mining trending terms from both the public Twitter timeline and from the timeline of tweets published by a user’s own Twitter friend subscriptions. We also present results of a live-user evaluation which demonstrates how these ranking strategies can add better item filtering and discovery value to conventional recency-based RSS ranking techniques.
      2078Scopus© Citations 69