The Latent Topic Block Model for the Co-Clustering of Textual Interaction Data

Abstract : In this paper, we consider textual interaction data involving two disjoint sets of individuals/objects. An example of such data is given by the reviews on web platforms (e.g. Amazon, TripAdvisor, etc.) where buyers comment on products/services they bought. We develop a new generative model, the latent topic block model (LTBM), along with an inference algorithm to simultaneously partition the elements of each set, accounting for the textual information. The estimation of the model parameters is performed via a variational version of the expectation maximization (EM) algorithm. A model selection criterion is formally obtained to estimate the number of partitions. Numerical experiments on simulated data are carried out to highlight the main features of the estimation procedure. Two real-world datasets are finally employed to show the usefulness of the proposed approach.
Type de document :
Pré-publication, Document de travail
Liste complète des métadonnées

Littérature citée [17 références]  Voir  Masquer  Télécharger
Contributeur : Marco Corneli <>
Soumis le : mercredi 11 juillet 2018 - 10:34:24
Dernière modification le : mercredi 10 octobre 2018 - 10:08:53
Document(s) archivé(s) le : vendredi 12 octobre 2018 - 17:21:59


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-01835074, version 1


Laurent Bergé, Charles Bouveyron, Marco Corneli, Pierre Latouche. The Latent Topic Block Model for the Co-Clustering of Textual Interaction Data. 2018. 〈hal-01835074〉



Consultations de la notice


Téléchargements de fichiers