metadata
library_name: transformers
license: apache-2.0
datasets:
- amazon-sales-dataset
language:
- en
metrics:
- accuracy
- f1
tags:
- text-classification
- sentiment-analysis
- ecommerce
- pytorch
- distilbert
Model Card for Model ID
Model Details
Model Description
This model is a fine-tuned version of distilbert-base-uncased on an Amazon product reviews dataset. It classifies customer reviews into two sentiment categories: Negative (label 0): rating < 3.5 Positive (label 1): rating ≥ 3.5 The model is designed to support automated customer service systems by providing real-time sentiment analysis.
- Developed by: Estella
- Model type: Text Classification
- Language(s) (NLP): English
- License: apache-2.0
- Number of Classes: 2
- 0: Negative
- 1: Positive
Intended Uses & Limitations
Intended Use:
- Sentiment analysis for e-commerce customer reviews
- Pre-processing step for automated reply generation or customer feedback dashboard
Limitations:
- The model was trained on product reviews from Amazon (electronics, cables, TVs, etc.). Performance on other domains (e.g., clothing, books) may vary.
- It does not detect neutral sentiment; reviews with rating 3.5 are considered positive by the chosen threshold.
How to Use the Model
You can use this model directly with the Transformers pipeline for text classification.
from transformers import pipeline
classifier = pipeline("text-classification", model="your_username/amazon-sentiment-distilbert")
result = classifier("This product is amazing!")
print(result) # [{'label': 'POSITIVE', 'score': 0.99}]