EUVIMEDEUVIMED entdecken
Crossref

Learning brand–celebrity fits in social networks for data-driven brand endorser selection

Zhen Wang, Zhen-Yu Chen

Enterprise Information Systems · 03.04.2026 · 20 (4)

DOI: 10.1080/17517575.2026.2644581 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Enterprise Information Systems, online erschienen am 17.03.2026. Verfasst von Zhen Wang und 1 weiteren Autor:innen. Die Arbeit nennt 58 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the internet celebrity economy, social network influence and the public image consistency are critical factors in brand endorser selection. This study proposes a data-driven brand endorser selection framework, that incorporates brand – celebrity fit metrics to measure the consistency of social relationships and public images between a brand and an endorser in social networks, and proposes three deep learning models to learn the brand – celebrity fits. Experiments results using data from 112 celebrities and 67 brands demonstrate the superior performance of the proposed model based on the brand – celebrity fits in social relationships and public images compared with baseline models.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Wang, Z., & Chen, Z. (2026). Learning brand–celebrity fits in social networks for data-driven brand endorser selection. Enterprise Information Systems, 20(4). https://doi.org/10.1080/17517575.2026.2644581

Vancouver

Wang Z, Chen Z. Learning brand–celebrity fits in social networks for data-driven brand endorser selection. Enterprise Information Systems. 2026;20(4). doi:10.1080/17517575.2026.2644581

BibTeX
@article{Wang2026,
  author = {Wang, Zhen and Chen, Zhen-Yu},
  title = {Learning brand–celebrity fits in social networks for data-driven brand endorser selection},
  journal = {Enterprise Information Systems},
  year = {2026},
  volume = {20},
  number = {4},
  doi = {10.1080/17517575.2026.2644581}
}
Kostenlos starten →