Inferring Dynamic User Interests in Streams of Short Texts for User Clustering

  • Journal/Conference Proceedings
    ACM Transaction on Information Systems
  • Publication Time
    August 2017
  • Authors
    Liang, Shangsong, Zhaochun Ren, Yukun Zhao, Jun Ma, Emine Yilmaz, and Maarten De Rijke.
We propose a dynamic user clustering topic model (UCT). UCT adaptively tracks changes of each user’s time-varying topic distributions based both on the short texts the user posts during a given time period and on previously estimated distributions. To infer changes, we propose a Gibbs sampling algorithm where a set of word pairs from each user is constructed for sampling.