Now showing 1 - 5 of 5
  • Publication
    Visualization of trends in subscriber attributes of communities on mobile telecommunications networks
    Churn, the decision for a subscriber to leave a provider, is frequently of interest in the telecommunications industry. Previous research provides evidence that social influence can be a factor in mobile telecommunications churn. In our work, presented at ASONAM, we presented a system, called ChurnVis, to visualize the evolution of mobile telecommunications churn and subscriber actions over time. First, we infer a social network from call detail records. Then, we compute components based on an overlay of this social network and churn activity. We compute summaries of the attributes associated with the subscribers and finally, we visualize the components in a privacy preserving way. The system is able to present summaries of thousands of churn components in graphs of hundreds of millions of edges. One of the drawbacks of the original approach was that churn components were sometimes very large, leading to over-aggregation in the summary data. In this extension of the ASONAM paper, we adapt the ChurnVis approach to operate on the output of a community finding algorithm and present new results based on this adaptation.
      471Scopus© Citations 5
  • Publication
    Learning-to-Rank for Real-Time High-Precision Hashtag Recommendation for Streaming News
    We address the problem of real-time recommendation ofstreaming Twitter hashtags to an incoming stream of newsarticles. The technical challenge can be framed as largescale topic classication where the set of topics (i.e., hashtags)is huge and highly dynamic. Our main applicationscome from digital journalism, e.g., for promoting originalcontent to Twitter communities and for social indexing ofnews to enable better retrieval, story tracking and summarisation.In contrast to state-of-the-art methods that focus onmodelling each individual hashtag as a topic, we propose alearning-to-rank approach for modelling hashtag relevance,and present methods to extract time-aware features fromhighly dynamic content. We present the data collection andprocessing pipeline, as well as our methodology for achievinglow latency, high precision recommendations. Our empiricalresults show that our method outperforms the state-of-theart,delivering more than 80% precision. Our techniques areimplemented in a real-time system1, and are currently underuser trial with a big news organisation.
    Scopus© Citations 30  2455
  • Publication
    Be In The Know: Connecting News Articles to Relevant Twitter Conversations
    In this paper we propose a framework for tracking and automatically connecting news articles to Twitter conversations as captured by Twitter hashtags. For example, such a system could alert journalists about news that get a lot of Twitter reaction, so they can investigate those conversations for new developments in the story, promote their article to a set of interested consumers, or discover general sentiment towards the story. Mapping articles to hashtags is nevertheless challenging, due to different language style of articles versus tweets, the streaming aspect, and user behavior when marking tweet-terms as hashtags. We track the Irish Times RSS-feed and a focused Twitter stream over a two months period, and present a system that assigns hashtags to each article, based on its Twitter echo. We propose a machine learning approach for classifying article hashtag pairs. Our empirical study shows that our system delivers high precision for this task.
      197
  • Publication
    Reformulations of the Map Equation for Community Finding and Blockmodelling
    Among the many community-finding algorithms that have been proposed in the last decade and more, the Infomapalgorithm of Rosvall and Bergstrom has proven among the best. The algorithm finds good community structure in directed aswell as undirected networks by abstracting information flow inthe network as a random walk. In this paper, we reformulate the objective in terms of the Kullback-Leibler distance between thedistribution of the random walk transitions and that of a modelwalk. The choice of model can be used to constrain the typeof partition that the method extracts. This generalisation makesthe method suitable for extracting other types of meso-structurefrom the network, enabling the analyst to explicitly control thetype of extracted structure.
    Scopus© Citations 2  312
  • Publication
    Overlapping Stochastic Community Finding
    Community finding in social network analysis is the task of identifying groups of people within a larger population who are more likely to connect to each other than connect to others in the population. Much existing research has focussed on non-overlapping clustering. However, communities in real world social networks do overlap. This paper introduces a new community finding method based on overlapping clustering. A Bayesian statistical model is presented, and a Markov Chain Monte Carlo (MCMC) algorithm is presented and evaluated in comparison with two existing overlapping community finding methods that are applicable to large networks. We evaluate our algorithm on networks with thousands of nodes and tens of thousands of edges.
    Scopus© Citations 3  367