Helping users discover perspectives: Enhancing opinion mining with joint topic models

Tim Draws, Jody Liu, Nava Tintarev

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

4 Citations (Scopus)
50 Downloads (Pure)


Support or opposition concerning a debated claim such as abortion should be legal can have different underlying reasons, which we call perspectives. This paper explores how opinion mining can be enhanced with joint topic modeling, to identify distinct perspectives within the topic, providing an informative overview from unstructured text. We evaluate four joint topic models (TAM, JST, VODUM, and LAM) in a user study assessing human understandability of the extracted perspectives. Based on the results, we conclude that joint topic models such as TAM can discover perspectives that align with human judgments. Moreover, our results suggest that users are not influenced by their pre-existing stance on the topic of abortion when interpreting the output of topic models.
Original languageEnglish
Title of host publication2020 International Conference on Data Mining Workshops (ICDMW)
EditorsL. O'Conner
Place of PublicationPiscataway
Number of pages8
ISBN (Electronic)978-1-7281-9012-9
ISBN (Print)978-1-7281-9013-6
Publication statusPublished - 2021
EventInternational Conference on Data Mining Workshops 2020 - Virtual/online event due to COVID-19, Sorrento, Italy
Duration: 2 Dec 20202 Dec 2020


ConferenceInternational Conference on Data Mining Workshops 2020
Abbreviated titleICDMW 2020

Bibliographical note

Virtual/online event due to COVID-19


  • debated topics
  • joint topic models
  • perspective discovery
  • sentiment analysis
  • topic modeling


Dive into the research topics of 'Helping users discover perspectives: Enhancing opinion mining with joint topic models'. Together they form a unique fingerprint.

Cite this