language: en license: apache-2.0 pipeline_tag: text-classification tags:
- sentiment-analysis
- distilbert
- transformers
- pytorch
DistilBERT Fine-Tuned for App Review Sentiment Classification
This model is a fine-tuned version of distilbert-base-uncased trained on the AARSynth app reviews dataset for sentiment classification.
Dataset
The model was trained on the AARSynth app reviews dataset containing app review sentences labeled with:
- Positive
- Neutral
- Negative
Model Details
- Backbone: distilbert-base-uncased
- Number of labels: 3
- Max sequence length: 128
- Batch size: 8
- Epochs: 3
- Learning rate: 2e-5
- Seed: 42
Evaluation Metrics
- Accuracy: 0.xx
- Macro-F1: 0.xx
Usage
from transformers import AutoTokenizer
from transformers import AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained(
"Deema100/m7-app-review-sentiment"
)
model = AutoModelForSequenceClassification.from_pretrained(
"Deema100/m7-app-review-sentiment"
)
Hugging Face Model
- Downloads last month
- 25