Tree-structured hierarchical Dirichlet process

Md Hijbul Alam, Jaakko Peltonen*, Jyrki Nummenmaa, Kalervo Järvelin

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

4 Citations (Scopus)


In many domains, document sets are hierarchically organized such as message forums having multiple levels of sections. Analysis of latent topics within such content is crucial for tasks like trend and user interest analysis. Nonparametric topic models are a powerful approach, but traditional Hierarchical Dirichlet Processes (HDPs) are unable to fully take into account topic sharing across deep hierarchical structure. We propose the Tree-structured Hierarchical Dirichlet Process, allowing Dirichlet process based topic modeling over a given tree structure of arbitrary size and height, where documents can arise at all tree nodes. Experiments on a hierarchical social message forum and a product reviews forum demonstrate better generalization performance than traditional HDPs in terms of ability to model new data and classify documents to sections.

Original languageEnglish
Title of host publicationDistributed Computing and Artificial Intelligence, Special Sessions, 15th International Conference
EditorsSara Rodríguez, Javier Prieto, Pedro Faria, María N. Moreno, Santiago Mazuelas, Elena M. Navarro, Slawomir Klos, Alberto Fernández, M. Dolores Jiménez-López
Number of pages9
ISBN (Print)9783319996073
Publication statusPublished - 1 Jan 2019
MoE publication typeA4 Conference publication
EventInternational Conference on Distributed Computing and Artificial Intelligence - Toledo, Spain
Duration: 20 Jun 201822 Jun 2018
Conference number: 15

Publication series

NameAdvances in Intelligent Systems and Computing
ISSN (Print)2194-5357


ConferenceInternational Conference on Distributed Computing and Artificial Intelligence
Abbreviated titleDCAI


  • Hierarchical Dirichlet Processes
  • Message forum
  • Topic modeling


Dive into the research topics of 'Tree-structured hierarchical Dirichlet process'. Together they form a unique fingerprint.

Cite this