GreekBERT for Text Classification

Developed by Team Trojan Parse University of Florida Senior Design Project

This is a model fine-tuned from luvnpce83/ancient-greek-emotion-bert for 8-class emotion text classification on ancient Greek. The model predicts one of eight basic emotions based on Plutchik’s Wheel of Emotions: Joy, Trust, Fear, Surprise, Sadness, Disgust, Anger, and Anticipation.

Project Information

  • Team Name: Trojan Parse
  • Team Members:
    • Alex John
    • Ryan Willson
    • Byron Boatright
    • Jake Marotta
    • Duncan Fuller
  • Project Repository: GitHub: Trojan-Parse-Project
  • Advisor: Eleni Bozia, Ph.D., Dr. phil. (Associate Professor of Classics and Digital Humanities)
  • Advisor Department: Department of Classics, University of Florida

Model Description

  • Model Name: greekbert_for_text_classification
  • Model type: BERT model for Ancient Language Text Classification
  • Language: Classical/Ancient Greek
  • Base model: luvnpce83/ancient-greek-emotion-bert
  • License: Llama 3.1 Community License
  • Purpose: Academic research and historical text analysis

Usage

from transformers import pipeline

classifier = pipeline("text-classification", model="rtwins/greekbert_for_text_classification")

result = classifier("ὦ ἀνόητοι Γαλάται")
print(result)
# [{'label': 'Anger', 'score': 0.8521...}]

Development

This model was developed by pseudo-labeling a large ancient Greek text corpus using luvnpce83/ancient-greek-emotion-bert. Labels greater than 0.90 confidence were taken and added to a bootstrapped training dataset. The base luvnpce83/ancient-greek-emotion-bert was then fine-tuned through training on this dataset. Unfortunately, knockdown errors have contributed to output flaws in the final model. Optimizations are in process

Performance

This model is lowly performant and needs improvements before being production ready

Testing

In progress

Acknowledgments

We would like to gratefully acknowledge:

  • Dr. Eleni Bozia (Ph.D., Dr. phil.) - Senior Project Advisor
  • University of Florida Department of Humanities - Computing resources and support

Citation

@phdthesis{kang2025emotions, author = {Kang, Young Un}, title = {Emotions in the Identity of Paul: A Sentiment Analysis Approach to Paul’s Jewish Identity}, school = {School of Theology, Yonsei University}, year = {2025} }

Downloads last month
2
Safetensors
Model size
0.1B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for rtwins/greekbert_for_text_classification

Finetuned
(1)
this model