Print Email Facebook Twitter Helping users discover perspectives Title Helping users discover perspectives: Enhancing opinion mining with joint topic models Author Draws, T.A. (TU Delft Web Information Systems) Liu, Jody (Student TU Delft) Tintarev, N. (TU Delft Web Information Systems) Contributor O'Conner, L. (editor) Date 2021 Abstract 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. Subject debated topicsjoint topic modelsperspective discoverysentiment analysistopic modeling To reference this document use: http://resolver.tudelft.nl/uuid:426eee20-2d7d-43b2-b405-7623a1c26343 DOI https://doi.org/10.1109/ICDMW51313.2020.00013 Publisher IEEE, Piscataway ISBN 978-1-7281-9013-6 Source 2020 International Conference on Data Mining Workshops (ICDMW) Event International Conference on Data Mining Workshops 2020, 2020-12-02, Virtual/online event due to COVID-19, Sorrento, Italy Bibliographical note Virtual/online event due to COVID-19 Part of collection Institutional Repository Document type conference paper Rights © 2021 T.A. Draws, Jody Liu, N. Tintarev Files PDF Helping_users_discover_pe ... models.pdf 470.04 KB Close viewer /islandora/object/uuid:426eee20-2d7d-43b2-b405-7623a1c26343/datastream/OBJ/view