EUVIMEDEUVIMED entdecken
Crossref

Multilingual Emotion Profiling of Large Language Models Through Literary Texts and Persona Conditioning

Naruki Shirahama, Yuma Yoshimoto, Naofumi Nakaya, Satoshi Watanabe

Journal of Advanced Computational Intelligence and Intelligent Informatics · 20.11.2026 · 30 (6) · 1866-1875

DOI: 10.20965/jaciii.2026.p1866 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Advanced Computational Intelligence and Intelligent Informatics, online erschienen am 20.11.2026. Verfasst von Naruki Shirahama und 3 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Gefördert von: Japan Society for the Promotion of Science.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper examines whether multilingual prompt-and-text conditions materially alter large language model (LLM) emotion evaluation rather than merely rephrasing the same task. Using OpenRouter as a unified inference layer, we evaluated six contemporary LLMs under three full-language conditions (Japanese, English, and Traditional Chinese), three literary texts, four personas, and three repeated API calls per condition. Each completion rated four emotional dimensions — Interesting, Surprise, Sadness, and Anger — and provided a brief rationale. The design comprised 648 planned evaluations (6 models × 3 languages × 3 texts × 4 personas × 3 trials). The final combined dataset contained 648 valid records, comprising 631 original records and 17 replacement records obtained under a repair amendment registered after the main run and before the patch run. Descriptive summaries and preregistered ordinary least squares analyses with HC3 robust standard errors showed that text content was a major driver of scores, especially for Sadness and Anger. Simultaneously, model-language interactions were significant for all four emotions, indicating that the effect of the language condition varied substantially across models. English yielded the highest mean Interesting, Surprise, and Sadness scores, whereas Japanese yielded the highest mean Anger score. However, these aggregate patterns mask the strong model-specific contrasts. The findings show that multilingual literary evaluation is shaped by both the text itself and the model processing of its translation. This study contributes a multilingual literary emotion benchmark, a preregistered and repair-aware evaluation pipeline, and evidence that multilingual conditions are substantive experimental factors for LLM emotion profiling.

Förderung

  • Japan Society for the Promotion of Science

Zitieren

APA

Shirahama, N., Yoshimoto, Y., Nakaya, N., & Watanabe, S. (2026). Multilingual Emotion Profiling of Large Language Models Through Literary Texts and Persona Conditioning. Journal of Advanced Computational Intelligence and Intelligent Informatics, 30(6), 1866-1875. https://doi.org/10.20965/jaciii.2026.p1866

Vancouver

Shirahama N, Yoshimoto Y, Nakaya N, Watanabe S. Multilingual Emotion Profiling of Large Language Models Through Literary Texts and Persona Conditioning. Journal of Advanced Computational Intelligence and Intelligent Informatics. 2026;30(6):1866-1875. doi:10.20965/jaciii.2026.p1866

BibTeX
@article{Shirahama2026,
  author = {Shirahama, Naruki and Yoshimoto, Yuma and Nakaya, Naofumi and Watanabe, Satoshi},
  title = {Multilingual Emotion Profiling of Large Language Models Through Literary Texts and Persona Conditioning},
  journal = {Journal of Advanced Computational Intelligence and Intelligent Informatics},
  year = {2026},
  volume = {30},
  number = {6},
  pages = {1866--1875},
  doi = {10.20965/jaciii.2026.p1866}
}
Kostenlos starten →