EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

High-accuracy, privacy-compliant multilingual sentiment categorization on consumer-grade hardware: A monte carlo evaluation of locally deployed large language models

Michele Carlo, Osamu Takeuchi

Digital Applied Linguistics · 2025

DOI: 10.29140/dal.v3.102585 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Digital Applied Linguistics, 2025. Verfasst von Michele Carlo und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study presents a comprehensive evaluation of multilingual sentiment categorization performance using locally deployed large language models (LLMs) on consumer-grade hardware, focusing on GDPR-compliant implementation scenarios. Through extensive Monte Carlo validation involving 947,700 classifications over 702 iterations, we demonstrate significant performance capabilities across English, Italian, and Japanese languages while operating within consumer hardware constraints. Using lightblue/suzume-llama-3-8B-multilingual-orpo-borda-half on a Python-based llama-cpp framework on consumer NVIDIA GPU hardware, English achieved 96.3% accuracy (95% CI: 0.963–0.964), with Italian and Japanese showing strong performance at 92.2% (95% CI: 0.921–0.922) and 90.7% (95% CI: 0.906–0.908) respectively. Notably, our analysis demonstrates that plurality voting can achieve extremely high confidence levels across all languages, suggesting an efficient approach to improving classification reliability without requiring extensive computational resources.

Zitieren

APA

Carlo, M., & Takeuchi, O. (2025). High-accuracy, privacy-compliant multilingual sentiment categorization on consumer-grade hardware: A monte carlo evaluation of locally deployed large language models. Digital Applied Linguistics. https://doi.org/10.29140/dal.v3.102585

Vancouver

Carlo M, Takeuchi O. High-accuracy, privacy-compliant multilingual sentiment categorization on consumer-grade hardware: A monte carlo evaluation of locally deployed large language models. Digital Applied Linguistics. 2025. doi:10.29140/dal.v3.102585

BibTeX
@article{Carlo2025,
  author = {Carlo, Michele and Takeuchi, Osamu},
  title = {High-accuracy, privacy-compliant multilingual sentiment categorization on consumer-grade hardware: A monte carlo evaluation of locally deployed large language models},
  journal = {Digital Applied Linguistics},
  year = {2025},
  doi = {10.29140/dal.v3.102585}
}
Kostenlos starten →