Cross-perspective Topic Modeling

An application that uses cross-perspective topic modeling to extract topics and opinions from text and provides insight into how they change over time.

10
mentions
3
contributors
Get started
13 commitsLast commit ≈ 107 months ago11 stars2 forks

What Cross-perspective Topic Modeling can do for you

  • Experiment with different settings
  • Generate iPython notebooks to visualize results
  • Downloading and preprocessing of the Dutch parliamentary proceedings

cptm is an implementation of cross-perspective topic modeling, which is is a topic modeling method that simultaneously extract topics and opinions from text. Topics are learned from nouns and opinions from adjectives. To use this tool, you need a corpus that is divided into perspectives. In the DiLiPaD project a perspective refers to a political party. We used this tool to extract topics and opinions from parliamentary proceedings.

Keywords
Programming languages
  • Python 93%
  • Jupyter Notebook 6%
  • Shell 1%
License
</>Source code

Participating organisations

Social Sciences & Humanities
Social Sciences & Humanities
Netherlands eScience Center
University of Amsterdam

Reference papers

Mentions

  • 1.
    Published in 2017
  • 2.
    Published in 2016
  • 3.
    Published in 2015
  • 4.
    Published in 2015
  • 5.
    Published in 2015

Contributors

Janneke van der Zwaan
Janneke van der Zwaan
LB
Lars Buitinck
Netherlands eScience Center

Related projects

DiLiPaD

A new approach to the history of parliamentary communication and discourse

Updated 21 months ago
Finished