HanfuZhao781/car-review-sentiment-distilbert

Car Review Sentiment, DistilBERT

distilbert-base-uncased fine-tuned for 3-class sentiment on real Edmunds car owner reviews, for a per-aspect word-of-mouth analyzer.

• —Labels: 0 negative, 1 neutral, 2 positive
• —Data: Edmunds consumer car reviews, florentgbelidji/car-reviews, labels by distant supervision from the 1 to 5 star rating.
• —Test set of 3,652 held-out reviews: accuracy 86.7 percent, macro-F1 0.566.
• —Known limits, measured: negation and sarcasm are hard. See the stress tests in the project repo. Deploy with confidence-gated abstention.

Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification import torch m = "HanfuZhao781/car-review-sentiment-distilbert" tok = AutoTokenizer.frompretrained(m) model = AutoModelForSequenceClassification.frompretrained(m) x = tok("The engine is powerful but the fuel economy is terrible", return_tensors="pt") print(model(**x).logits.softmax(-1))

App: https://HanfuZhao781-car-review-sentiment.hf.space Code: https://github.com/hanfuzhao/Module2-CarReviewSentiment

Built for the 540 Summer Module 2 hackathon.