Advanced search
2 files | 2.49 MB Add to list

Hybrid transformer-based recommender system for political news

Stefaan Vercoutere (UGent) , Toon De Pessemier (UGent) and Luc Martens (UGent)
Author
Organization
Abstract
This study investigates a nudging-based news recommender designed to broaden exposure to political articles while preserving user satisfaction. We built a hybrid transformer-based recommender system that combines content-based embeddings (via a custom transformer architecture) with click-behavior signals to refine user profiles. A dedicated profile extension module augments each profile with semantically related concepts, subtly steering recommendations toward political news according to user-existing interests. In an online experiment with 168 participants, our nudging system significantly outperformed a popularity-based baseline (satisfaction: +12.84%, political clicks: +15.35%) and an interest-based baseline (satisfaction: +6.96%, political clicks: +6.44%). Notably, participants with the lowest initial political interest exhibited the largest engagement gains (clicks: +64.54% over popularity, +22.75% over interest) without compromising user satisfaction.
Keywords
INFORMATION OVERLOAD, News recommender systems, Selection diversity, Nudging, Knowledge graphs

Downloads

  • (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.49 MB
  • WICA 1303a.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 1.00 MB

Citation

Please use this url to cite or link to this publication:

MLA
Vercoutere, Stefaan, et al. “Hybrid Transformer-Based Recommender System for Political News.” JOURNAL OF INTELLIGENT INFORMATION SYSTEMS, vol. 63, no. 5, 2025, pp. 1569–601, doi:10.1007/s10844-025-00951-7.
APA
Vercoutere, S., De Pessemier, T., & Martens, L. (2025). Hybrid transformer-based recommender system for political news. JOURNAL OF INTELLIGENT INFORMATION SYSTEMS, 63(5), 1569–1601. https://doi.org/10.1007/s10844-025-00951-7
Chicago author-date
Vercoutere, Stefaan, Toon De Pessemier, and Luc Martens. 2025. “Hybrid Transformer-Based Recommender System for Political News.” JOURNAL OF INTELLIGENT INFORMATION SYSTEMS 63 (5): 1569–1601. https://doi.org/10.1007/s10844-025-00951-7.
Chicago author-date (all authors)
Vercoutere, Stefaan, Toon De Pessemier, and Luc Martens. 2025. “Hybrid Transformer-Based Recommender System for Political News.” JOURNAL OF INTELLIGENT INFORMATION SYSTEMS 63 (5): 1569–1601. doi:10.1007/s10844-025-00951-7.
Vancouver
1.
Vercoutere S, De Pessemier T, Martens L. Hybrid transformer-based recommender system for political news. JOURNAL OF INTELLIGENT INFORMATION SYSTEMS. 2025;63(5):1569–601.
IEEE
[1]
S. Vercoutere, T. De Pessemier, and L. Martens, “Hybrid transformer-based recommender system for political news,” JOURNAL OF INTELLIGENT INFORMATION SYSTEMS, vol. 63, no. 5, pp. 1569–1601, 2025.
@article{01KMZ24EX9F4AH0KT3X5NCQJAG,
  abstract     = {{This study investigates a nudging-based news recommender designed to broaden exposure to political articles while preserving user satisfaction. We built a hybrid transformer-based recommender system that combines content-based embeddings (via a custom transformer architecture) with click-behavior signals to refine user profiles. A dedicated profile extension module augments each profile with semantically related concepts, subtly steering recommendations toward political news according to user-existing interests. In an online experiment with 168 participants, our nudging system significantly outperformed a popularity-based baseline (satisfaction: +12.84%, political clicks: +15.35%) and an interest-based baseline (satisfaction: +6.96%, political clicks: +6.44%). Notably, participants with the lowest initial political interest exhibited the largest engagement gains (clicks: +64.54% over popularity, +22.75% over interest) without compromising user satisfaction.}},
  author       = {{Vercoutere, Stefaan and De Pessemier, Toon and Martens, Luc}},
  issn         = {{0925-9902}},
  journal      = {{JOURNAL OF INTELLIGENT INFORMATION SYSTEMS}},
  keywords     = {{INFORMATION OVERLOAD,News recommender systems,Selection diversity,Nudging,Knowledge graphs}},
  language     = {{eng}},
  number       = {{5}},
  pages        = {{1569--1601}},
  title        = {{Hybrid transformer-based recommender system for political news}},
  url          = {{http://doi.org/10.1007/s10844-025-00951-7}},
  volume       = {{63}},
  year         = {{2025}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: