language: en
thumbnail: https://huggingface.co/nsi319
tags:
- distilbert
- pytorch
- text-classification
- mobile
- app
- descriptions
- playstore
- classification
license: mit
inference: true
Mobile App Classification
Model description
DistilBERT is a transformer model, smaller and faster than BERT, which was pre-trained on the same corpus in a self-supervised fashion, using the BERT base model as a teacher.
The distilbert-base-uncased model is fine-tuned to classify an mobile app description into one of 6 play store categories. Trained on 9000 samples of English App Descriptions and associated categories of apps available in Google Play.
Fine-tuning
The model was fine-tuned for 5 epochs with a batch size of 16, a learning rate of 2e-05, and a maximum sequence length of 512. Since this was a classification task, the model was trained with a cross-entropy loss function. The best evaluation f1 score achieved by the model was 0.9034534096919489, found after 4 epochs. The accuracy of the model on the test set was 0.9033.
How to use
from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
tokenizer = AutoTokenizer.from_pretrained("nsi319/distilbert-base-uncased-finetuned-app")
model = AutoModelForSequenceClassification.from_pretrained("nsi319/distilbert-base-uncased-finetuned-app")
classifier = pipeline('sentiment-analysis', model=model, tokenizer=tokenizer)
classifier("From scores to signings, the ESPN App is here to keep you updated. Never miss another sporting moment with up-to-the-minute scores, latest news & a range of video content. Sign in and personalise the app to receive alerts for your teams and leagues. Wherever, whenever; the ESPN app keeps you connected.")
'''Output'''
[{'label': 'Sports', 'score': 0.9959789514541626}]
Limitations
Training data consists of apps from 6 play store categories namely Education, Entertainment, Productivity, Sports, News & Magazines and Photography.