metadata
language:
- en
- tl
tags:
- sentiment-analysis
- filipino
- english
- roberta
- service-reviews
license: mit
datasets:
- custom
metrics:
- accuracy
- f1
pipeline_tag: text-classification
HandyHome Sentiment Analysis
This model classifies sentiment in Filipino-English service reviews.
Model Details
- Base Model: RoBERTa
- Task: Sentiment Classification (3 classes)
- Languages: Filipino, English (mixed)
- Classes:
- 0: Negative
- 1: Neutral
- 2: Positive
Usage
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
# Load model and tokenizer
model_name = "YOUR_USERNAME/handyhome-sentiment-roberta"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)
# Predict sentiment
text = "Magaling yung service, very professional!"
inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512)
with torch.no_grad():
outputs = model(**inputs)
predictions = torch.softmax(outputs.logits, dim=1)
predicted_class = torch.argmax(predictions, dim=1).item()
labels = ["negative", "neutral", "positive"]
print(f"Sentiment: {labels[predicted_class]}")
Training Data
Trained on HandyHome service reviews dataset containing Filipino-English mixed language reviews.