hsisaberi/single-trait-electra
A complete ELECTRA-based framework for Big Five personality trait recognition, featuring data augmentation, single-trait model training, k-fold cross-validation, grid search optimization, inference tools, and full reproducibility of the associated research article.
This project helps researchers and social scientists analyze text data, like essays, to determine an author's Big Five personality traits (Openness, Conscientiousness, Extraversion, Agreeableness, Neuroticism). You feed it text samples, and it provides predictions for each trait. It's designed for psychologists, linguists, and anyone studying personality through written communication.
Use this if you need to automatically identify Big Five personality traits from written text and want to build or validate robust models using advanced machine learning techniques.
Not ideal if you are looking for a simple, off-the-shelf personality assessment tool without needing to engage with model training or evaluation.
Stars
18
Forks
1
Language
Python
License
MIT
Category
Last pushed
Jan 07, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/hsisaberi/single-trait-electra"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MaartenGr/BERTopic
Leveraging BERT and c-TF-IDF to create easily interpretable topics.
webis-de/small-text
Active Learning for Text Classification in Python
mead-ml/mead-baseline
Deep-Learning Model Exploration and Development for NLP
x-tabdeveloping/turftopic
Robust and fast topic models with sentence-transformers.
HumanSignal/label-studio-transformers
Label data using HuggingFace's transformers and automatically get a prediction service