Horror-Fear-RoBERTa

This model is a RoBERTa-based classifier fine-tuned on horror game reviews to detect fear intensity.

Usage:

from transformers import AutoModelForSequenceClassification, AutoTokenizer
model = AutoModelForSequenceClassification.from_pretrained("namurice/horror-fear-roberta")
tokenizer = AutoTokenizer.from_pretrained("namurice/horror-fear-roberta")

text = "I couldn't stop shaking after playing this level."
inputs = tokenizer(text, return_tensors="pt")
outputs = model(**inputs)
logits = outputs.logits
probs = logits.softmax(dim=-1)
fear_score = probs[0, 1].item()  # assuming label 1 is 'fear'
print(f"Fear intensity: {fear_score:.2f}")