Text Classification
Transformers
Safetensors
English
roberta
sentiment-analysis
restaurant-reviews
text-embeddings-inference
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("Almashtouly/Restaurant_RoBERTa_Model")
model = AutoModelForSequenceClassification.from_pretrained("Almashtouly/Restaurant_RoBERTa_Model")Quick Links
Restaurant Review RoBERTa Classifier
Model Description
This is a fine-tuned version of roberta-base trained specifically to analyze the sentiment of restaurant and hospitality reviews. It was trained to understand the specific nuances, slang, and context of food service feedback.
- Developed by: Almashtouly
- Model type: RoBERTa Sequence Classification
- Language: English
- License: MIT
Uses
This model is intended for analyzing customer feedback in the restaurant and hospitality industry.
Direct Use
Pass raw text reviews into the model to classify them into three categories:
- LABEL_0: Negative (e.g., "The steak was completely undercooked.")
- LABEL_1: Neutral (e.g., "The food was okay, nothing special.")
- LABEL_2: Positive (e.g., "The ambiance and service were absolutely incredible!")
How to Get Started with the Model
You can easily use this model in your own applications via the Hugging Face pipeline:
from transformers import pipeline
# Load the model
analyzer = pipeline("text-classification", model="Almashtouly/Restaurant_RoBERTa_Model")
# Test a review
prediction = analyzer("The waitstaff was incredibly friendly, but the food took way too long.")
print(prediction)
- Downloads last month
- 31
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Almashtouly/Restaurant_RoBERTa_Model")