EUVIMEDEUVIMED entdecken
Crossref

Investigating Personality-Aware Calibration Across Domains and Recommendation Approaches

Yuvisa Quispe Palomino, Paul Atauchi, Marcelo Garcia Manzato

ACM SIGAPP Applied Computing Review · 01.06.2026 · 26 (2) · 21-34

DOI: 10.1145/3828534.3828536 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM SIGAPP Applied Computing Review, online erschienen am 14.07.2026. Verfasst von Yuvisa Quispe Palomino und 2 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recommender systems (RS) help users make decisions among the huge amount of information available online, but they can also reinforce existing preferences, contributing to filter bubbles and popularity bias. Calibration can mitigate this issue by aligning recommendations with users' preference distributions; however, when it relies only on historical interactions, its diversity gains depend on how diverse the user profile already is. This paper extends our previous personality-aware calibration approach by examining whether Big Five traits provide complementary signals across domains and recommendation approaches. We evaluate the method using movie and music datasets, considering collaborative filtering and content-based models. The results indicate that personality-aware calibration can reduce miscalibration and improve global utility in both domains, although its effects vary across algorithms and calibration settings. In collaborative filtering, the observed effects are mainly associated with semantic diversity and reduced miscalibration. In the content-based setting, the gains are more evident in reduced miscalibration, long-tail coverage, popularity alignment, and overall utility. Overall, personality traits offer useful complementary signals for producing more balanced recommendations beyond users' historical behavior.

Zitieren

APA

Palomino, Y. Q., Atauchi, P., & Manzato, M. G. (2026). Investigating Personality-Aware Calibration Across Domains and Recommendation Approaches. ACM SIGAPP Applied Computing Review, 26(2), 21-34. https://doi.org/10.1145/3828534.3828536

Vancouver

Palomino YQ, Atauchi P, Manzato MG. Investigating Personality-Aware Calibration Across Domains and Recommendation Approaches. ACM SIGAPP Applied Computing Review. 2026;26(2):21-34. doi:10.1145/3828534.3828536

BibTeX
@article{Palomino2026,
  author = {Palomino, Yuvisa Quispe and Atauchi, Paul and Manzato, Marcelo Garcia},
  title = {Investigating Personality-Aware Calibration Across Domains and Recommendation Approaches},
  journal = {ACM SIGAPP Applied Computing Review},
  year = {2026},
  volume = {26},
  number = {2},
  pages = {21--34},
  doi = {10.1145/3828534.3828536}
}
Kostenlos starten →