XTRA: eXplainable Text-based Recommendation Algorithm
Applied Computer Systems · 01.01.2026 · 31 (1) · 127-137
DOI: 10.2478/acss-2026-0011 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Computer Systems, online erschienen am 13.06.2026. Verfasst von Hasan Serhat Gunduz und 2 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Recommendation systems built on ratings often fail to fully exploit the rich information contained in textual reviews and social-platform content. Text provides not only an additional signal for ranking, but also a natural basis for generating explanations. This study introduces XTRA, a rating-free, text-driven recommendation system that derives user relationships from shared review content and transforms sentiment expressed in text into personalized recommendation decisions. The proposed approach also incorporates explainability mechanisms to clarify both why users are considered similar and how textual sentiment contributes to the final recommendation. Experimental results on Amazon-Beauty, Yelp-Illinois, and IMDB-20K show that XTRA outperforms strong rating-based baselines on Yelp and IMDB, while remaining competitive on Amazon. These findings indicate that textual signals can serve as an effective alternative to ratings while also supporting transparent and interpretable recommendations. Implementation details are provided to support reproducibility and future extension.
Zitieren
APA
Gunduz, H. S., Bozanta, A., & Yucel, O. (2026). XTRA: eXplainable Text-based Recommendation Algorithm. Applied Computer Systems, 31(1), 127-137. https://doi.org/10.2478/acss-2026-0011
Vancouver
Gunduz HS, Bozanta A, Yucel O. XTRA: eXplainable Text-based Recommendation Algorithm. Applied Computer Systems. 2026;31(1):127-137. doi:10.2478/acss-2026-0011
BibTeX
@article{Gunduz2026,
author = {Gunduz, Hasan Serhat and Bozanta, Aysun and Yucel, Osman},
title = {XTRA: eXplainable Text-based Recommendation Algorithm},
journal = {Applied Computer Systems},
year = {2026},
volume = {31},
number = {1},
pages = {127--137},
doi = {10.2478/acss-2026-0011}
}
EUVIMED